diff --git a/.gitattributes b/.gitattributes index 875d410d12314f19c6507c9ca2c130e49c582ef5..771f456389a4163500945024110ad5a1cf67340c 100644 --- a/.gitattributes +++ b/.gitattributes @@ -17565,3 +17565,209 @@ neuronxcc-2.24.5133.0+58f8de22/MODULE_5983480387230594376+bad9cf09/model.neff fi neuronxcc-2.24.5133.0+58f8de22/MODULE_7343260162999572602+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.24.5133.0+58f8de22/MODULE_7903529212460185893+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.24.5133.0+58f8de22/MODULE_8173596499745875930+bad9cf09/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/unet/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/unet/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/unet/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/03b0c107d1cede36875199a5d51decfe04c473de2af9999f8577a028d74d0ab4/ec1560a24138c907085c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/03b0c107d1cede36875199a5d51decfe04c473de2af9999f8577a028d74d0ab4/ec1560a24138c907085c.json new file mode 100644 index 0000000000000000000000000000000000000000..bad82609a4c8953d25d534b8729b0027f61a97d5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/03b0c107d1cede36875199a5d51decfe04c473de2af9999f8577a028d74d0ab4/ec1560a24138c907085c.json @@ -0,0 +1,189 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "_task": "image-text-to-text", + "architectures": [ + "Idefics3ForConditionalGeneration" + ], + "dtype": "bfloat16", + "image_token_id": 49190, + "model_type": "idefics3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "checkpoint_revision": "7e3e67edbbed1bf9888184d9df282b700a323964", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 64, + "image_size": 512, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 2048, + "max_num_images": 17, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "scale_factor": 4, + "text_config": { + "_attn_implementation_autoset": false, + "_flash_attn_2_enabled": true, + "_name_or_path": "None", + "architectures": [ + "VLlama3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 576, + "initializer_range": 0.041666666666666664, + "intermediate_size": 1536, + "is_llama_config": true, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "neftune_noise_alpha": 0.0, + "num_attention_heads": 9, + "num_hidden_layers": 30, + "num_key_value_heads": 3, + "pad_token_id": 2, + "perceiver_config": { + "_attn_implementation_autoset": false, + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "silu", + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "vllama3", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_key_value_heads": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "qk_layer_norms_perceiver": false, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "resampler_depth": 6, + "resampler_head_dim": 96, + "resampler_n_heads": 16, + "resampler_n_latents": 64, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.46.0", + "typical_p": 1.0, + "use_bfloat16": false + }, + "pixel_shuffle_factor": 4, + "pretraining_tp": 1, + "qk_layer_norms": false, + "rms_norm_eps": 1e-05, + "rope_interleaved": false, + "rope_scaling": null, + "rope_theta": 100000, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "use_resampler": false, + "vocab_size": 49280 + }, + "tie_word_embeddings": false, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "vision_config": { + "_attn_implementation_autoset": false, + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 768, + "image_size": 512, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-06, + "max_image_size": { + "longest_edge": 512 + }, + "model_type": "idefics3_vision", + "num_attention_heads": 12, + "num_channels": 3, + "num_hidden_layers": 12, + "patch_size": 16, + "size": { + "longest_edge": 2048 + }, + "tie_word_embeddings": false, + "use_base_siglip": true + }, + "vocab_size": 49280 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/04e22cfac37c408caa51d61b493ee185fc351c2f9db86171e024b5d0ad5b25c1/c56a8bce0577ce31a594.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/04e22cfac37c408caa51d61b493ee185fc351c2f9db86171e024b5d0ad5b25c1/c56a8bce0577ce31a594.json new file mode 100644 index 0000000000000000000000000000000000000000..84c8a9548b1d66209f8318273b54d0621c516a9e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/04e22cfac37c408caa51d61b493ee185fc351c2f9db86171e024b5d0ad5b25c1/c56a8bce0577ce31a594.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-qwen3", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 36, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-qwen3", + "checkpoint_revision": "81d6f5f5e05ed53ea8a1d19431266a486e46bbd8", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/2132439b615164bef4eb.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/2132439b615164bef4eb.json new file mode 100644 index 0000000000000000000000000000000000000000..453e3c777f92d081a72755b1482049097c695c7a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/2132439b615164bef4eb.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "dtype": "bfloat16", + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/da74b3645f29f4218169.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/da74b3645f29f4218169.json new file mode 100644 index 0000000000000000000000000000000000000000..699e9645d89f7c438b7806ce525ed1642e7a691e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/da74b3645f29f4218169.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "dtype": "bfloat16", + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6ed6aa77ee480d24287c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6ed6aa77ee480d24287c.json new file mode 100644 index 0000000000000000000000000000000000000000..355c8460ae8515ab986c6b4072dd0cef6653e1d4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/6ed6aa77ee480d24287c.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": true, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/748542be1bcc5fe3cdf1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/748542be1bcc5fe3cdf1.json new file mode 100644 index 0000000000000000000000000000000000000000..addf85f038ecf11ca378d8f4b977833896843999 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/748542be1bcc5fe3cdf1.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/9a130a0e2b7177d1dea1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/9a130a0e2b7177d1dea1.json new file mode 100644 index 0000000000000000000000000000000000000000..58a525a22f63920e976058ec6a99a8366f842717 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/441269935591cad8d370e512c0b93cdd2fce6247c40e5a4866d872ee5338b0de/9a130a0e2b7177d1dea1.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/196ef14bd9a3e0d3035c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/196ef14bd9a3e0d3035c.json new file mode 100644 index 0000000000000000000000000000000000000000..3cf32f254609d8ff5fb03f93624fe66697e0171c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/196ef14bd9a3e0d3035c.json @@ -0,0 +1,83 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/3474ddeda6545f7e5db7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/3474ddeda6545f7e5db7.json new file mode 100644 index 0000000000000000000000000000000000000000..f71af41682f300db77e507cb8b6d45f7a45cf711 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/3474ddeda6545f7e5db7.json @@ -0,0 +1,83 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/0d1cbffb3e66b482c261.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/0d1cbffb3e66b482c261.json new file mode 100644 index 0000000000000000000000000000000000000000..828d7f089030d4494e72c3d294d2456f7ef5223f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/0d1cbffb3e66b482c261.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "feature-extraction", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 6, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B", + "checkpoint_revision": "97b0c614be4d77ee51c0cef4e5f07c00f9eb65b3", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 6, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151669 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/61ff8eae2078e66cabfd.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/61ff8eae2078e66cabfd.json new file mode 100644 index 0000000000000000000000000000000000000000..5834efe8b4cb3613ee010cd781d815cfcbc623b2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/61ff8eae2078e66cabfd.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "feature-extraction", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B", + "checkpoint_revision": "97b0c614be4d77ee51c0cef4e5f07c00f9eb65b3", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151669 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/24892d985c7b4406e3d9.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/24892d985c7b4406e3d9.json new file mode 100644 index 0000000000000000000000000000000000000000..3a5f041729ccd315d9ce05b60c6f15a12ea2078c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/24892d985c7b4406e3d9.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/dedf7a5ae53bb6e1b3fc.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/dedf7a5ae53bb6e1b3fc.json new file mode 100644 index 0000000000000000000000000000000000000000..1d8bbd0d364536a1e660d2fb1cf3c064abfae13a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/dedf7a5ae53bb6e1b3fc.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 128, + "max_topk": 256, + "n_active_tokens": 128, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 128, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn2", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/df8b960809b8e9d97bd2.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/df8b960809b8e9d97bd2.json new file mode 100644 index 0000000000000000000000000000000000000000..1d3fef01c2f9f494c0c66183db598cee214041f0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/6454afdf3e9d66c7226c13a575b718845c25e53b0699600ba2bb4f883e9d841b/df8b960809b8e9d97bd2.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 512, + "max_topk": 256, + "n_active_tokens": 512, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 512, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/309698d1c71c3e0c8eb8.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/309698d1c71c3e0c8eb8.json new file mode 100644 index 0000000000000000000000000000000000000000..44fb38f3c9fa8ed52e360ac435524a82a3944fc4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/309698d1c71c3e0c8eb8.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/8d67a5db932b99602641.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/8d67a5db932b99602641.json new file mode 100644 index 0000000000000000000000000000000000000000..8d5511b0964dd18a268bd6b8b3efb595c47ae2ec --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/73707b485eab9008c7aba7f5dad0ce2384ac685318d5f888c12fa0d81ed90b19/8d67a5db932b99602641.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/0b70cb2cd9d99c1bdf34.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/0b70cb2cd9d99c1bdf34.json new file mode 100644 index 0000000000000000000000000000000000000000..9976d0cfbbf67383248249a3f56165c1557a7394 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/0b70cb2cd9d99c1bdf34.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/805a8935ea4fbf9c4df6.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/805a8935ea4fbf9c4df6.json new file mode 100644 index 0000000000000000000000000000000000000000..b4a65c5a36cec5d421ac06787da9e42335540b06 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/805a8935ea4fbf9c4df6.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 1, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 1 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/fd610699b7c75d5fa5cc.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/fd610699b7c75d5fa5cc.json new file mode 100644 index 0000000000000000000000000000000000000000..fdfe1fb289123a9236086ad24212d938f4b8cae5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/fd610699b7c75d5fa5cc.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/5df183a9a537186b793f.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/5df183a9a537186b793f.json new file mode 100644 index 0000000000000000000000000000000000000000..d7de9bfb131f7d639bd4eeecedd4efc1ecf982fa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/5df183a9a537186b793f.json @@ -0,0 +1,169 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "/home/tengomucho/.cache/huggingface/hub/models--echarlaix--tiny-random-stable-diffusion-xl/snapshots/434a0025554940d46ddd5dd10f0abc2788076b47/vae", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "output_hidden_states": true, + "vocab_size": 1000 + }, + "text_encoder_2": { + "architectures": [ + "CLIPTextModelWithProjection" + ], + "attention_dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-with-projection", + "hidden_act": "gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "output_hidden_states": true, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": "text_time", + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": 8, + "attention_head_dim": [ + 2, + 4 + ], + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 64, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": 80, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": [ + 1, + 2 + ], + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": true + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/73e765061ca0edc0984c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/73e765061ca0edc0984c.json new file mode 100644 index 0000000000000000000000000000000000000000..e5859016e4b38f0b12a1275a687e2b96b7768d45 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/73e765061ca0edc0984c.json @@ -0,0 +1,125 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "/home/tengomucho/.cache/huggingface/hub/models--hf-internal-testing--tiny-stable-diffusion-torch/snapshots/a88cdfbd91f96ec7f61eb7484b652ff0f4ee701d/vae", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/c6310bffbfbf29e5d927.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/c6310bffbfbf29e5d927.json new file mode 100644 index 0000000000000000000000000000000000000000..cbaa15b7bf6770f9cfcece82af47da9bf448077b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/b191d607e94819566800de30939d6c26cefbebc52bef9ff571aa1855a9ca0a4e/c6310bffbfbf29e5d927.json @@ -0,0 +1,124 @@ +{ + "_entry_class": "MultiModelCacheEntry", + "_model_id": "/home/tengomucho/.cache/huggingface/hub/models--echarlaix--tiny-random-latent-consistency/snapshots/ea16e1fcf89fe667eef6639bfd14ac8701bff7b9/vae", + "_task": null, + "text_encoder": { + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "dtype": "float32", + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 8, + "num_hidden_layers": 3, + "vocab_size": 1000 + }, + "unet": { + "_class_name": "UNet2DConditionModel", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 4, + 8 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 1, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 2, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "time_cond_proj_dim": 32, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/190c48cba7eeccd29748.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/190c48cba7eeccd29748.json new file mode 100644 index 0000000000000000000000000000000000000000..2e3fbe5483b80f288d38b74088ac7b03b847dade --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/190c48cba7eeccd29748.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 4096, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/4709e472b680eafc6cc9.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/4709e472b680eafc6cc9.json new file mode 100644 index 0000000000000000000000000000000000000000..451278e767de62eb7710eb8312d6a5af28ba2a0a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/4709e472b680eafc6cc9.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/552e8cb4a475fa6bf79e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/552e8cb4a475fa6bf79e.json new file mode 100644 index 0000000000000000000000000000000000000000..7c3c836af941d9b4373616fb412492928e75256a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/552e8cb4a475fa6bf79e.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/d391df1950611ad2a02d.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/d391df1950611ad2a02d.json new file mode 100644 index 0000000000000000000000000000000000000000..5919a012c3b95b7e1a23942e8a3a482e3bdbbc5e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/d391df1950611ad2a02d.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": null, + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 4096, + "max_topk": 256, + "n_active_tokens": 4096, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 4096, + "speculation_length": 5, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0a07fcbaaaca6e450fabdb638553525f4bfb07bcac85320ca02556f31cd98cf/68b8b60ad74d23a1ba59.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0a07fcbaaaca6e450fabdb638553525f4bfb07bcac85320ca02556f31cd98cf/68b8b60ad74d23a1ba59.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0af5b0213151145f29f04252fc03d445d0647d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/e0a07fcbaaaca6e450fabdb638553525f4bfb07bcac85320ca02556f31cd98cf/68b8b60ad74d23a1ba59.json @@ -0,0 +1,130 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-4b-it", + "_task": "image-text-to-text", + "architectures": [ + "Gemma3ForConditionalGeneration" + ], + "boi_token_index": 255999, + "dtype": "bfloat16", + "eoi_token_index": 256000, + "image_token_index": 262144, + "initializer_range": 0.02, + "mm_tokens_per_image": 256, + "model_type": "gemma3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-4b-it", + "checkpoint_revision": "bf46152c47f5dd20b896357cb51abc4c03b8ee8c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 256, + "image_size": 896, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 2048, + "max_num_images": 5, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "text_config": { + "_sliding_window_pattern": 6, + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 10240, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention" + ], + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 8, + "num_hidden_layers": 34, + "num_key_value_heads": 4, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": { + "factor": 8.0, + "rope_type": "linear" + }, + "rope_theta": 1000000.0, + "sliding_window": 1024, + "sliding_window_pattern": 6, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262208 + }, + "unsloth_fixed": true, + "vision_config": { + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "image_size": 896, + "intermediate_size": 4304, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 27, + "patch_size": 14, + "vision_use_head": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/unsloth/gemma-3-4b-it/68b8b60ad74d23a1ba59.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/unsloth/gemma-3-4b-it/68b8b60ad74d23a1ba59.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0af5b0213151145f29f04252fc03d445d0647d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3/unsloth/gemma-3-4b-it/68b8b60ad74d23a1ba59.json @@ -0,0 +1,130 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-4b-it", + "_task": "image-text-to-text", + "architectures": [ + "Gemma3ForConditionalGeneration" + ], + "boi_token_index": 255999, + "dtype": "bfloat16", + "eoi_token_index": 256000, + "image_token_index": 262144, + "initializer_range": 0.02, + "mm_tokens_per_image": 256, + "model_type": "gemma3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-4b-it", + "checkpoint_revision": "bf46152c47f5dd20b896357cb51abc4c03b8ee8c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 256, + "image_size": 896, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 2048, + "max_num_images": 5, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "text_config": { + "_sliding_window_pattern": 6, + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2560, + "initializer_range": 0.02, + "intermediate_size": 10240, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention" + ], + "max_position_embeddings": 131072, + "model_type": "gemma3_text", + "num_attention_heads": 8, + "num_hidden_layers": 34, + "num_key_value_heads": 4, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": { + "factor": 8.0, + "rope_type": "linear" + }, + "rope_theta": 1000000.0, + "sliding_window": 1024, + "sliding_window_pattern": 6, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262208 + }, + "unsloth_fixed": true, + "vision_config": { + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 1152, + "image_size": 896, + "intermediate_size": 4304, + "layer_norm_eps": 1e-06, + "model_type": "siglip_vision_model", + "num_attention_heads": 16, + "num_channels": 3, + "num_hidden_layers": 27, + "patch_size": 14, + "vision_use_head": false + } +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/748542be1bcc5fe3cdf1.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/748542be1bcc5fe3cdf1.json new file mode 100644 index 0000000000000000000000000000000000000000..addf85f038ecf11ca378d8f4b977833896843999 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/gemma3_text/unsloth/gemma-3-270m-it/748542be1bcc5fe3cdf1.json @@ -0,0 +1,82 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/gemma-3-270m-it", + "_sliding_window_pattern": 6, + "_task": "text-generation", + "architectures": [ + "Gemma3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": null, + "dtype": "bfloat16", + "final_logit_softcapping": null, + "head_dim": 256, + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 640, + "initializer_range": 0.02, + "intermediate_size": 2048, + "layer_types": [ + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "model_type": "gemma3_text", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "unsloth/gemma-3-270m-it", + "checkpoint_revision": "23cf460f6bb16954176b3ddcc8d4f250501458a9", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_local_base_freq": 10000.0, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 512, + "unsloth_fixed": true, + "use_bidirectional_attention": false, + "use_cache": true, + "vocab_size": 262144 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/granite/ibm-granite/granite-3.1-2b-instruct/2132439b615164bef4eb.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/granite/ibm-granite/granite-3.1-2b-instruct/2132439b615164bef4eb.json new file mode 100644 index 0000000000000000000000000000000000000000..453e3c777f92d081a72755b1482049097c695c7a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/granite/ibm-granite/granite-3.1-2b-instruct/2132439b615164bef4eb.json @@ -0,0 +1,59 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "ibm-granite/granite-3.1-2b-instruct", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.1, + "attention_multiplier": 0.015625, + "dtype": "bfloat16", + "embedding_multiplier": 12.0, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "logits_scaling": 8.0, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "ibm-granite/granite-3.1-2b-instruct", + "checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 40, + "num_key_value_heads": 8, + "residual_multiplier": 0.22, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": true, + "use_cache": true, + "vocab_size": 49155 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/ec1560a24138c907085c.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/ec1560a24138c907085c.json new file mode 100644 index 0000000000000000000000000000000000000000..bad82609a4c8953d25d534b8729b0027f61a97d5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/idefics3/HuggingFaceTB/SmolVLM-256M-Instruct/ec1560a24138c907085c.json @@ -0,0 +1,189 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "_task": "image-text-to-text", + "architectures": [ + "Idefics3ForConditionalGeneration" + ], + "dtype": "bfloat16", + "image_token_id": 49190, + "model_type": "idefics3", + "neuron": { + "_serialized_key": "NxDVLMNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolVLM-256M-Instruct", + "checkpoint_revision": "7e3e67edbbed1bf9888184d9df282b700a323964", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "image_seq_len": 64, + "image_size": 512, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 2048, + "max_num_images": 17, + "max_topk": 256, + "n_active_tokens": 2048, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 2048, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "scale_factor": 4, + "text_config": { + "_attn_implementation_autoset": false, + "_flash_attn_2_enabled": true, + "_name_or_path": "None", + "architectures": [ + "VLlama3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 576, + "initializer_range": 0.041666666666666664, + "intermediate_size": 1536, + "is_llama_config": true, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "neftune_noise_alpha": 0.0, + "num_attention_heads": 9, + "num_hidden_layers": 30, + "num_key_value_heads": 3, + "pad_token_id": 2, + "perceiver_config": { + "_attn_implementation_autoset": false, + "_name_or_path": "", + "add_cross_attention": false, + "architectures": null, + "attention_dropout": 0.0, + "bad_words_ids": null, + "begin_suppress_tokens": null, + "bos_token_id": null, + "chunk_size_feed_forward": 0, + "cross_attention_hidden_size": null, + "decoder_start_token_id": null, + "diversity_penalty": 0.0, + "do_sample": false, + "early_stopping": false, + "encoder_no_repeat_ngram_size": 0, + "eos_token_id": null, + "exponential_decay_length_penalty": null, + "finetuning_task": null, + "forced_bos_token_id": null, + "forced_eos_token_id": null, + "hidden_act": "silu", + "id2label": { + "0": "LABEL_0", + "1": "LABEL_1" + }, + "is_decoder": false, + "is_encoder_decoder": false, + "label2id": { + "LABEL_0": 0, + "LABEL_1": 1 + }, + "length_penalty": 1.0, + "max_length": 20, + "min_length": 0, + "model_type": "vllama3", + "no_repeat_ngram_size": 0, + "num_beam_groups": 1, + "num_beams": 1, + "num_key_value_heads": 1, + "num_return_sequences": 1, + "output_attentions": false, + "output_hidden_states": false, + "output_scores": false, + "pad_token_id": null, + "prefix": null, + "problem_type": null, + "pruned_heads": {}, + "qk_layer_norms_perceiver": false, + "remove_invalid_values": false, + "repetition_penalty": 1.0, + "resampler_depth": 6, + "resampler_head_dim": 96, + "resampler_n_heads": 16, + "resampler_n_latents": 64, + "return_dict": true, + "return_dict_in_generate": false, + "sep_token_id": null, + "suppress_tokens": null, + "task_specific_params": null, + "temperature": 1.0, + "tf_legacy_loss": false, + "tie_encoder_decoder": false, + "tie_word_embeddings": true, + "tokenizer_class": null, + "top_k": 50, + "top_p": 1.0, + "torch_dtype": null, + "torchscript": false, + "transformers_version": "4.46.0", + "typical_p": 1.0, + "use_bfloat16": false + }, + "pixel_shuffle_factor": 4, + "pretraining_tp": 1, + "qk_layer_norms": false, + "rms_norm_eps": 1e-05, + "rope_interleaved": false, + "rope_scaling": null, + "rope_theta": 100000, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "use_resampler": false, + "vocab_size": 49280 + }, + "tie_word_embeddings": false, + "transformers.js_config": { + "kv_cache_dtype": { + "fp16": "float16", + "q4f16": "float16" + } + }, + "use_cache": true, + "vision_config": { + "_attn_implementation_autoset": false, + "attention_dropout": 0.0, + "hidden_act": "gelu_pytorch_tanh", + "hidden_size": 768, + "image_size": 512, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_norm_eps": 1e-06, + "max_image_size": { + "longest_edge": 512 + }, + "model_type": "idefics3_vision", + "num_attention_heads": 12, + "num_channels": 3, + "num_hidden_layers": 12, + "patch_size": 16, + "size": { + "longest_edge": 2048 + }, + "tie_word_embeddings": false, + "use_base_siglip": true + }, + "vocab_size": 49280 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/llamafactory/tiny-random-Llama-3/24892d985c7b4406e3d9.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/llamafactory/tiny-random-Llama-3/24892d985c7b4406e3d9.json new file mode 100644 index 0000000000000000000000000000000000000000..3a5f041729ccd315d9ce05b60c6f15a12ea2078c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/llamafactory/tiny-random-Llama-3/24892d985c7b4406e3d9.json @@ -0,0 +1,63 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "float16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 1, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 1, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "float16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/552e8cb4a475fa6bf79e.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/552e8cb4a475fa6bf79e.json new file mode 100644 index 0000000000000000000000000000000000000000..7c3c836af941d9b4373616fb412492928e75256a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/552e8cb4a475fa6bf79e.json @@ -0,0 +1,64 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "unsloth/Llama-3.2-1B-Instruct", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct", + "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": true, + "unsloth_fixed": true, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/Qwen/Qwen2.5-0.5B/3474ddeda6545f7e5db7.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/Qwen/Qwen2.5-0.5B/3474ddeda6545f7e5db7.json new file mode 100644 index 0000000000000000000000000000000000000000..f71af41682f300db77e507cb8b6d45f7a45cf711 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/Qwen/Qwen2.5-0.5B/3474ddeda6545f7e5db7.json @@ -0,0 +1,83 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": false, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/Qwen/Qwen3-0.6B/0b70cb2cd9d99c1bdf34.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/Qwen/Qwen3-0.6B/0b70cb2cd9d99c1bdf34.json new file mode 100644 index 0000000000000000000000000000000000000000..9976d0cfbbf67383248249a3f56165c1557a7394 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/Qwen/Qwen3-0.6B/0b70cb2cd9d99c1bdf34.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-0.6B", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 40960, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-0.6B", + "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/61ff8eae2078e66cabfd.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/61ff8eae2078e66cabfd.json new file mode 100644 index 0000000000000000000000000000000000000000..5834efe8b4cb3613ee010cd781d815cfcbc623b2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/Qwen/Qwen3-Embedding-0.6B/61ff8eae2078e66cabfd.json @@ -0,0 +1,88 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen3-Embedding-0.6B", + "_task": "feature-extraction", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 1024, + "initializer_range": 0.02, + "intermediate_size": 3072, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 28, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "Qwen/Qwen3-Embedding-0.6B", + "checkpoint_revision": "97b0c614be4d77ee51c0cef4e5f07c00f9eb65b3", + "continuous_batching": false, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 8192, + "max_topk": 256, + "n_active_tokens": 8192, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 1024, + "sequence_length": 8192, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 16, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151669 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/llamafactory/tiny-random-qwen3/c56a8bce0577ce31a594.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/llamafactory/tiny-random-qwen3/c56a8bce0577ce31a594.json new file mode 100644 index 0000000000000000000000000000000000000000..84c8a9548b1d66209f8318273b54d0621c516a9e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen3/llamafactory/tiny-random-qwen3/c56a8bce0577ce31a594.json @@ -0,0 +1,62 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-qwen3", + "_task": "text-generation", + "architectures": [ + "Qwen3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_types": [ + "full_attention", + "full_attention" + ], + "max_position_embeddings": 32768, + "max_window_layers": 36, + "model_type": "qwen3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 2, + "capacity_factor": null, + "checkpoint_id": "llamafactory/tiny-random-qwen3", + "checkpoint_revision": "81d6f5f5e05ed53ea8a1d19431266a486e46bbd8", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 2, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": false, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000, + "sliding_window": null, + "tie_word_embeddings": true, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/8d67a5db932b99602641.json b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/8d67a5db932b99602641.json new file mode 100644 index 0000000000000000000000000000000000000000..8d5511b0964dd18a268bd6b8b3efb595c47ae2ec --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/smollm3/HuggingFaceTB/SmolLM3-3B/8d67a5db932b99602641.json @@ -0,0 +1,135 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "HuggingFaceTB/SmolLM3-3B", + "_task": "text-generation", + "architectures": [ + "SmolLM3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 65536, + "max_window_layers": 28, + "mlp_bias": false, + "model_type": "smollm3", + "neuron": { + "_serialized_key": "NxDNeuronConfig", + "batch_size": 4, + "capacity_factor": null, + "checkpoint_id": "HuggingFaceTB/SmolLM3-3B", + "checkpoint_revision": "a07cc9a04f16550a088caea529712d1d335b0ac1", + "continuous_batching": true, + "ep_degree": 1, + "fused_qkv": true, + "glu_mlp": true, + "local_ranks_size": 2, + "max_batch_size": 4, + "max_context_length": 1024, + "max_topk": 256, + "n_active_tokens": 1024, + "neuronxcc_version": "2.26.6360.0+6f180f47", + "on_device_sampling": true, + "optimum_neuron_version": "0.4.7.dev0", + "output_logits": false, + "pp_degree": 1, + "prefill_chunk_size": 0, + "sequence_length": 1024, + "speculation_length": 0, + "start_rank_id": 0, + "target": "trn1", + "torch_dtype": "bfloat16", + "tp_degree": 2 + }, + "no_rope_layer_interval": 4, + "no_rope_layers": [ + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0, + 1, + 1, + 1, + 0 + ], + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 4, + "pretraining_tp": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 5000000.0, + "sliding_window": null, + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8708f500fa9dbe3756e648878839741ef1621ff5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d79208a5da7edaccc8bba759c74eccd6a0ef1b42 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df61ceb956b65ffc93d7765ba86a6aacb1b771a8bacfddb7fa06002ebb021f6c +size 1691021 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c22d7d49e0df3eb0654d2de1bbf02486b71d8dfb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_008268ac9b472a8ee1b2+97496b47/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e49a709e1ea870cad2e693b9c13b9e9a07ce0061b0a8ae3e8f132023e91218b9 +size 26420224 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8797c8db2427543293bcc304d6a1692851d671d3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f23b364d4879cb413e0fbdd2dfb4dfeaa0821888feced3735fcfe5031b9d03d +size 2432816 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..60ea7c9bfc69609fd191256e34a836701abfa0cc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b85ab2243de6c32a2756c56e7bf0171f30edb11c4024c6029ab9e66629ba0b +size 2653184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..51e2016cb01e2dfd3444e461152c741c9d3e318e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0568499afedbce2755d2+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d3af7468affc34917a69e6713422ce841d8e7f7234ac3e1ed3a455b4f67a1e8 +size 2813329 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5e3f9abdc6811167f6ecc33364c6d162ffbde653 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2009d90c5bd844c6f809f4e1f1d14185d7548f1ea10cc2f277b199cbfb87999d +size 4072999 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..290d4bdab56086d0174adcf5cb30d9b6a1e207c5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0632e5fdcca8738ae989+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1387132ea6b27caeeb099b293087d980122bea90a995475995d9c320819f029a +size 12145664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..66b598473d4df44c09d6193776fed8739cdbf209 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02e764e999a0b451333e1f5cec5c0fbdf70a0757d5e397bede3bc5d6753dd68 +size 2704584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6203f18ffd2e9cb2d599821cb7445992ba4e74ae --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_06618d6c5e8bd5e409c0+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4472d5d11238e2df79c92ebaf84985ce2cda42513875eb83c38bf1130a4e83 +size 2868224 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fb47297eee1c31c82e64bee6b5306f27c928f412 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49415345b31fc58b63fa97eedbd0e154030646174a75a340df7c7381036fb383 +size 2205837 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fed39468e2aa7f28ff094b6af43d1e4256da7232 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_073e3ae283183bf46f7e+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d749eb090d75258d951da3454ff4307eabf2427e7f86bb69e8d500799a8d99 +size 2632704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..757ef22adba051caf9112fe25b606c7fcd78c660 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:432507cb832f7729bbf0ea778b0674fbbcec5e2c99bc215a74bc9e18388ea0a7 +size 2769192 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..717d3321f4a14f87d505429b25af21ec08eaf70e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_098c7b2bb282dd07336b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08c2bffc8a4d4c372373af82a0d606c45371e8d5f1606a47deb19229175be9d7 +size 7640064 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..82ffb7cbbb811418fe322fcf3dc95f77584d86f5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b0c54fd448d01bfaca6a8c8f89d6d230b2a35479ba7329ab752b71d93572c8 +size 1384895 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f115860bc1075f4a4831bea3c2d79772f5afa5ff --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f6011b6eedff21ecc70740a16b05e428af899706eea5343eb529417a0fbe13 +size 1946624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1a2f02d18c7dc862370dda291e294d44e0c7efb1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0a0e90258cde52021d6c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c21a269073f2ec6aba8a67d542e7016e29fed9b50c611071237bc66e825b240 +size 2039537 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a9790cd58bfb20d885359d0bbc4f900926b03dd8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfc6c8d490cd17282445a8c5a7d48c44c5f8cd6d01f4a08c5c056ba21bba3877 +size 157192 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..912531c26666945cdefe02d3a7b02f223b781f1e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:583492cdbc8011c3e8a7399a57c2c901033f842fce27158ff8b4daa346f3f63a +size 205824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fcbd98b51bbe727fd849ac60bafddfcb021bd8da --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0ad611735b0e10f907be+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b6a309368147634336d212f7d5abf1a5344b9e7a837146f800f7d42944a819e +size 211973 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ae763d12a4cfe8446bc201c1c714feda58cddbce --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def8b3cd6426dcd13af1bae673ef19cb37238a1ce0d9850e5d5520bf45fb9eea +size 2507511 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0719c51cb143987ce9c22943d8c05fd74a5b1882 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b792381fa453c715f2ae0912e373d85c106c19d6a4c9bca46d3ea12d85472cd +size 2376704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8a344e13887c7814a5c0ecf427179b20952a906d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b4c7dcdd85918a819c3+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28dc7dd5a6603546636aba3019e0405db9a09ae43c24635f2b4c50cb140da7e8 +size 2513872 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/vision_encoder/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2f5ea3f27d22f0dffde95a80bbaae89614d69118 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77d7527c374754842fb157f1531f6d47354f8d8d3eec04c02d83fc496e30b0d +size 676521 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..17960b9872bc817edb7a785682017bcc8ee381cd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c147f1d18841ea08cf0031d87b492445c10dba8a5204d737fee4c56a56a8a52d +size 11490304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2f9966c3dd8dd81531e03bd80d9e522ae944dae5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0b6b86331e957bacee2d+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ed462da0bafb053540539cfd20a6e0e033ff241bf5716a4db70569360d6fd6 +size 11600469 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1b8d0a06e1a041b717613013c76b26a4d23a83a1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fd390636def08c539736def2a71a304f759867554101a059b587ed68e8edcd1 +size 1854512 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..135251b5015c24186810e4bc7da4a96ef6f0b647 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_0f5a9802a78ccacfe236+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e85d3956e86326834ad37770c70d46465d1731a0d62e91e29e69da5699d53893 +size 10783744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..32157f229be17480afc9e02a7ed48ca0cbc8f22a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d6cf01433f86f2e63e06abf77f0f55466bd8dafa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6f390a6952e02624697a77b670161540dc7c55c302c1c9fa2bf21131500e8c +size 2539 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..99e4eb1e174a10236e7d80f3d6cd8b337cd21863 Binary files /dev/null and b/neuronxcc-2.26.6360.0+6f180f47/MODULE_12345434034474459279+e30acd3a/model.neff differ diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6ddca070600857a4a8baa6d9c8cc90b28a36270d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d36689230c337980fe99df46f149ed7a272b5522c8cdcae9c7d1bae04e69fb0 +size 2767073 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..777d55ae10baba0015463660bcb5913e57f91db1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1411a1bcc1201278ff08+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91dd030dcee3c05cd0af50b0140a6303607500aa0293bb96fdf9e79dd01fae4a +size 7967744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..66951240abe0fe05228b5e1ea9e3c473c11d438c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8cd679f23c93f7c17bf1a3af4119084fbc692c0730fa35f26395874e2ec4310 +size 2470226 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e0a4863eb566ae933f3fd6f835e8bbb2a1814a2e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:633d4c6e2642b0d0395c071a1a0a78bf39d270b83e9a7d555b7099b1c9a50324 +size 1823744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..01f444899907ca6310886d8b7b005db9db80e7c0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_147a9ca8d0079fe60a3f+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe9c79db1e619f821c9330b1539afe5112c459349a4a20edbb580e1007198a30 +size 1934622 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..aa62a0a1853aed0709ce2febf0251ebf2dec769c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:602c04e7d8b255f1a4ebaf4f805d749ad3fe97704c2395ba4211cd73b9cc8fa6 +size 2004637 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..df860769b019ae629ae934d69fdbdf97b11eeb91 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_165ddf347e87727e1e3f+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010d5e4493594af52cf4480d370f2053ca7d25deb5726d3e1da3bd2e2f3b9e85 +size 3410944 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ff2f731a7c2917d22e55fc1ce6eb8c3ebe73296e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6673225a21202410c25cb3d5393e37968bf9bfaf3b0651410284582131acc190 +size 2029038 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..82e8e4b4238d696c0349b30846f81aeb15b39465 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_17bdfe7645d8e87128ff+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d189984b1c9c766732ed244d98cf4e0cfaf3564ce7ba9e8676a83de1443b2e9c +size 3410944 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..91fe16eaec348823e46292ff48083e41533aea5b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c89c12ac8e9d535f3e104d18529542875465ab04680b5116882999a4c89bf11 +size 2769048 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3f67f058b0ca7dee120f84ee8c026b52895d8fa2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_186a5c4840fd4d6f90d4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba9699778492c5b80fabdfa844e21d1846b42cd01a45ff916e2c49cb2ec77b2 +size 8018944 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..511e8949aa5a907e512fe94891399ebe9e6f7099 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d9b83390315b80f7e2e31e7e91c128a7701f182d1525f6f798c170128b7c319 +size 2164083 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4c4378121005a8c0ec3206ec4505475a7e18ecb9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1a965de2dabb48c57dfe469e337c97ae7713ba855845774f7724d199b2a0708 +size 1649664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..25b9ae04c15f46baaa83365e82768fe2128390fe --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_19787c71cd7be643f3f9+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d16bdd33dec5504dcd8cba600e8d4e5f50cdaadccffbd739b6d1df691d2a306 +size 1805855 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ca2002d7158d98e12f2af7b78a00b19520665cf4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:682fde39dd388b97be0388a0e7315e59904436ee6101f94251ca59c3f0b86771 +size 1844527 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..33e92257986f6b44113bbe12ec73b702c4a5a919 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a95f4126d9851f3be3907d9d36d66446b211ae2fa7e6ee53aac3b9b57c79370 +size 1373184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b714bdeb8961958b18d0c1c46acb493454b3396a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_1eb086c415411ddf9914+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c16c1c48ed703f1ae029825c08170e5b116dce4033600da543b4b9e4565444 +size 1495658 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ad82c3e4810a40f2fe346ca3e9ca4673fff1fcd5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf76725cf4aed49731fe847e5391ca9ff0d1be5fdd188bcf48bac441996eaf90 +size 1877438 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..949de51387c9752aed0f7ad94467e146d249dfa6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0729939462c1c2f0279240784319f1a4e8d13e44ce8619308480ab79ff50b4 +size 1373184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..79e27e64a4a10687deb4373894c34e491454e82c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_21dad3fc72fb243184b9+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:436ea39af68d5adf6e82e04b3d3c5a639dca7d985b782980458911445dae713e +size 1495658 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..398ef216b17745eb9b862c29692c77c4768ebd80 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39c0d664108e487eacbcdebe58ea0761f6a2d8f44dd19fd7879a00be703b4de7 +size 3417344 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6a8af7401ed474e4dfd7626b75d775549af2d6d2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_24186092e38c4b24437c+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1b6972897b390fc35e6a846a51f355eb503b45d9f1585ad6533054524659329 +size 12381184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a32519332eefc1f0b55c2a219eb3917aa992848c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd658312cf75933279ed565ed65518547a406348d401efa8674d4f392d3ce3f +size 3326676 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..140a56f1a1358a41b97a3e55ea0b0b7149ab5731 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_266d2d16441fb5da6c03+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04be365cda29f4b7de173c3e1aae7fa6705cb98963576015c81eebdc7535ba85 +size 5069824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..32157f229be17480afc9e02a7ed48ca0cbc8f22a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1298d272f7b00b600172c2d704e2c71c506455af --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdd9c1eb16459fb27210afa969f2f30642004f5b95af073b673d0965abf14212 +size 7756 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a6fcc91d44185c23be12bec59b5769906c4f0471 Binary files /dev/null and b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2726995351478512444+e30acd3a/model.neff differ diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..33e80ac676b49ca1775f3823bf266a4c5092cff6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10814c58dca19fb9c21a023a7ea51ac5912627411c304450df986e42b1ae21e6 +size 2413554 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..2b124b7d6c450f8374faf7b2625b9e532a49ea34 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea7cdf7fa7c70578a3d17cd7b350c8b622720d1368c7ee30ee750812e2d4cf03 +size 2653184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f8a2c2ea0a8bb178a956bb2398dc14d3b535908d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_28f077d239104f60dc85+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f4891a0399d45f435b0585488d5e79e2a2fae4771119079ca4b84972c3433d9 +size 2813329 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..14db990a0fce880bbfa09e9b90ff8bb4951b862c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98fc54e59a2740f3c66d97be40c5c2ecd6d9745440e77bf383c2a35f92e009f8 +size 2161561 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a24ef9754354b8009b533e2f5ad9a9e07d7943d1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5b3a6e966f3f1359e3e2b5a30383ffb56cb627005755867c4088e3048fb72d3 +size 1649664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3022f158850eb431b32074ba5aa2be0a8f29db3d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_293aaa3b245c1b274ddc+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba653223c78de7576fcb1a2c269fbe3d652e2855495c591e4ca6e8e58c35f7a9 +size 1805855 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a8bcbe82caaa9a0857fe2669d2845a47b8e26f09 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a6231a9ca08ba6557f4b3acae5ec6d877383b27338dba04cd5a3dfc97ebec9a +size 3062433 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8e178e04f49e01d6b3e17d57eb33a13ccd27923c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd32f38b25f695d51ba09f564c94edfe8e8268ad5dcfcee91db36cf5bb2d98dd +size 5305344 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0075730a151a6827003cbdedbcde17b845bcefbf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2c9d7390c9520ec1c42e+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b6e7a32550e6b731ce39fab63c402657f136e8a3457e821114138c9de4fef36 +size 5471868 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4b4a480daf2e126ac61351df9431cfca7ab35521 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c3ba7b7c20ff80c5168f8de97f4efa2d58902c53111f7322b2797c13ccc6fd +size 1451765 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b96b78c08eec56e65f239f8a0a718b6dac0d99ac --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8329d1b49bb9ba30adcd32e13428240bf07933af75ba4f74aad45dbe85ccf7db +size 2243584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fae236967d3bb4b3de8b0f9b1c55753c7b056289 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_2e0432da842e548ced4d+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6b2142a3ecc7d9b9fd5d4ca7256a82ec93ceff30534570a32088e34e6a60cda +size 2317783 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8ccbd9f57fcb5db2be4b5d6c0d31afcc463cc2e1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c0c27110ffdb44e851b88a0346e2ddfc3b43d5a334278681e78537cc7550a79 +size 2488417 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d32deebebde0558336091dedd191e59a3f344bf7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1368d5d59eac1e4e3b1e3068aa867e7ff980a94d09c43f283621393a0a64003f +size 2376704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d11385eae194006a858ed1e2c9ca56d080acfa14 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_30b02c94c40715ef1413+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eab583c45ac7f1f2c32e6b75f7c8d25894cc53cae0ff6e1b30e5743684a7ff1 +size 2513872 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e28e4a3637aa7e0c96c56c30b4e73416fa25cf28 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0458f6e84149c42760428fb3c55cb7b6832ddab3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a6fc533269b6f9653c44f680c4b8f506809c81e8d005f6e265b1bc9cfb5479 +size 272044 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fd8edeac07ca632812b656d8ee93fda2b15c576e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04da6b75740e8a9aa4b37c10e0b977f8c824103a8fa62b85d38edfdc467cd577 +size 374414 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cd1cafeadb38443e8ddd66d1412976bfe543cfd7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33832659c4841cf2f06f+4a27301b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ece6379f14596fe315bc86a7e322ffb211fd5a2e45b959e74768d1b0ae20df62 +size 382210 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c29b51fcd1694a380f19e8b82bc766389f96abb6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85910e4dfed248839b3b10cb1ad3d5c8187a9ad1e8b3a17ea19725136a58e553 +size 1879038 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3e2a4ea86bb86a7ce7a0a11a37b0e5497afa72a0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_33a2a1d2f2d8e8e49e1a+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78591ba4ca28c45951f7f2ec1f93ec92109613c08fb93517bfb1d258c0174595 +size 10783744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..522ef98e7011150ff0ff6e008b0115a287520071 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8af3702a2e2bf18bd9dcc189b9edf7cf4947e14b64e4594e167e144948473770 +size 4902030 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a04c49701d872f7674af64f932313102da397b2d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_37b3ce1ee47af005bebe+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c508342ff82bc08860d2b197a4c8521275b0215ca5f37fe2c56a1fb04c4955ed +size 10947584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4b2909f42d1d588b2a89ba538375d5ff9e54be27 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b7ccaa53e171b54c7e52d71aba50ef9d1c2880e74a5beb0cd2e3f8a1d888b3b +size 2218383 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..528e9e332250f3082819afddbf01f54623a515df --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65cb326424ba2b50eb56df4ac99b54db1b3c6ecfbc583d027866b4d9b0c32505 +size 1700864 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..cdd8cd6b36cacb1707e67f197cccd3e4526e6a56 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38b27aaf11cf4045906c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222e7972a4c1dedc0d46a6315063ad5c72000c360774d3775fa2e45c0f1e201e +size 1857170 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dcb4db4cf4ff9f26a89ee4f2650f4095656de7aa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3db2cb75542e2fb7c1e2e9d2f1691c9fb3b2c563d8361bf33c25de7a1c62133 +size 1993756 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d112332b739fdf2ef45cb99a22a821cffd526fba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_38fae39fa3848a54e884+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ab29f1c0e8d2e49a6802ef816ef771f21ded2cdf4e59579264c7d0dc91a43a2 +size 2970624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5ebafc31f5ab888da336672b1f1a55ca30702353 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6ba935d16b10ccdf6f8caca4d18fd6519a2eeb24994c0e5a17892efbfdc6729 +size 3710415 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4f452d6864f6b3a1d7402fda5aaf1ac3fe9c68c9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd24d01d88ad0520498a12f5648c69cad4f37ea41aa098c8e01897291a802708 +size 5131264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..289b50c7eb9f996df662f919da1929315b7c0219 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_3a82adf89377a01449f1+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d350250fce84f752d5fa586902007e63686c5bbd4b2ad22adb2d72d306c20fd8 +size 5315443 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/vision_encoder/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..896cb5569e636de23e901a68d98bb5ad898826ce --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a29bedf23c1fc475c8ca023f448fec6f3dc542d91e6a20ec10bb0098fe70a13a +size 677702 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..89b57cd4a14630ba08aa99e56ab761103258bf0b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c3d552a7a02bf6cfadab6c53e9432b4d4d3ff2fc69b7e6ada38b16f858eb55d +size 11500544 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..bf900c6d601bec8f572599c71f8adda0c2c44a20 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_40c4614ec10cdf609375+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd5278e009e777b9e74ad386e4237733ae721c18d47d1009a1fd11ed605c69b3 +size 11610709 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..42afe50226ccb6988c6ed5655386fa74709229b7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86be4fa85f596ca3808ac9c27a98622a7f295e785ca9480a9a05af224fc62079 +size 2514444 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..48054bc4b62c76c885c68fdc2147c7c955003388 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:246ec4059380442e32782d9da0242fcb87626bc21c72a24307179dfa9263f0fe +size 2376704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a3d6649a7e57e4171529b8887912d7e7f6a8f752 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_41a3183aaa9c2cbe3e28+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f7147229fc24cd2c6e9bf446d46436448fffa62a950db203c96e92bf5136fac +size 2513872 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..cd78bd3b5de2549dcb0af3b71e14a6c8261f87ec --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2a3f47170e180d8a049b0619652b1c50b70eaeee8ddfe58581b9df0cbd3d6b1 +size 1296870 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..636425927485daa0daba0e8688c9df6c362438d9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4323097dc248ba27d8c6+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffd74966410b726e867c4277a7cf2ed192f6140b529971b9f29acc149f442131 +size 3267584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a16f8359e0fc1c11ed079e10ff1fece2f5ac9d31 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac14f2444ec558fd621c23879dcd629a69a078d7cbf8452fb68127f84db17cbf +size 2280735 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a93a81ef685aa9bdd9de9f520a7e39a997fa65ff --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29892c82944cd7adac11f0ad2c94503050b9a8214cdaca7259b80f311bde2c89 +size 3277824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ce6eb6cc70b459a234096702935ed5514ee58d96 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_442b55a691221bdb4b08+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849a4963da02977a6904f1794eb8325b4894ccea0a970f75b84df866dcbb8acf +size 3415603 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ac555b701b3954656d35f76f79783d25ea049594 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfe3c061e2393283bab6c2fd58599dc98302cb56d598f3d87520fbe81d7f3146 +size 1464040 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6021ffea100e1be38beec954bab5dbbc7bbb32b2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e856e821a5b292e2110fa8af26a62c32f7c416b1a2b2a50c6b2f6542ad2290f4 +size 2305024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ca9c03f9e91b7ee1a834396cb14d626e39257dae --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_44512bdd426602e62ce9+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:414dfe9ed0df3faa3fb6d44ce1f19add12998ac0cc28b2f36052148907932268 +size 2379111 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2d318f4c867a7fe8cc87a4f26f335245bc5d02d8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae101b24edc24e3520f5b4c1456b7f7f78677e8a5cf0ca1ee1d070843d9030d8 +size 1869518 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f577e1554b3b1de1a364823f43f7ddf3a4150551 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_45b435f72e0037ca46a2+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db7d55f03ef564a54c03732072efbc1cb49c912e0b07a30cbddbfb49a81713e4 +size 10783744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e5c829238cb266352287645955b1f074de42c58a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2627dce527832dbdb1497c61a5cdaee1d0f7b02140ac543a93f66510f1357957 +size 195287 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..df73324247f835b6a393f02119ce54e9d8c2176f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_497252034e9743a5ba18+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f32e1ad61ad1f8da22fd44a647d3df3f1dcc4b4bb9b9d17f88e421651340b05c +size 318464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..f392e945f61aae750695432118161df1e671cc47 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f1ea7d33d14db4507e66a3e1bab25314a505196043ad3a6ceec47f98b54cda8 +size 2710378 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ab4642ee7c3991588338b5bc05630d64927626b0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a11e1ef3adf1ceb9513+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0d2ae67e940f949b64a5d48f938c44d208dfd0da08cee4469e8d444ba124abd +size 2868224 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/vision_encoder/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6e9a3a4d3c1c67ba1ca0d1679152ed83056ea271 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1690ec0496431e6bdd1424cfe999b1d91cf802feee68ac73e377046381dba504 +size 1846025 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d9872bcda4015b1439360632cf5977fcafbee9b3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be232e3963221ad454c25f0e260f63babb9351590dc0a80430a7f49a4073c39c +size 22928384 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..06b234898f1dc27bef4783b9bf338bf7036994fc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4a3055fc5c1fd109487a+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8885219d5033cbe37fe68bc415c0c7c668d921a7890746a4b1d167ceece5f544 +size 23161502 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9fca84ad6acb4cde79e1ea598899c30cd387c9d8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40920b77f9af889a58fff5aa45249b8a45c50d6dec9dac0a3998325fcbc8d985 +size 1832501 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dcb260db432b95a429fb418215b6e56922cb3799 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a573186fe5462db34f2bdcb5ae994c48be088ca51b832d5ac44441336af96a9 +size 1158144 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d07aa19d35c0fb02a4d6ebee41f5b5a986df40bc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4b27b2b060ee68419d2a+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf42972bbb747fde2ad9a4ae44fff57eb07f0b6179e9222541ba0430c07ea72f +size 1280533 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..900a71d685463405a3e02f732cae1f1b44ab0d8c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ec316b88da871f13c8e55ea185a9e52504fc3a166518660524cee1ac5d5667 +size 3264132 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..7add9129c3678087f12c0cc3e59f2d15d5627ef6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4c65baafff130ed529cb+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:369b280451d2b6eaef2e495c6cd779ae5f30e028141835655f2bd408e6d3bada +size 19303424 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d614f688e68797bb9c0b098c344ca081c3c30f15 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b93bc610ed6e2b2c6523d6ec8d37f4e66d3b6f277809f66b86e857783284ff5 +size 2800179 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b8c1539171ba07b04a597d016423ec9698fad641 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4df48492d35e4ffb8a16+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b742c94d05ba5ecf96c93ceb10b822e42e3be072007bbc5de0fe74ce0b8c8afd +size 7967744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ab533a56eb05e72aa75e9e85e2d28746d6d4b7bd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb20740e6d6877b39f29d92dbeabaf3806f60cddf2d02919c12c0de144bb432c +size 3661853 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..98826cc80fdb50c930ff9303f0e49caa9e0ee996 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bcf7cf69f7ea76f9fc5fc0ed2b142c792c64af627057a50a1e39791d85c741d +size 4936704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..2ad856c265f8b6e292614d19bba24f13254b0cda --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4e4db5fd3765679de86e+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e390579043b3f5f72e3e4e8cb684cb1e42666f8d5258b5bab286d507f78207cc +size 5121163 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c7881867b0b12ec68d753b548a8d881d7f881083 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:907918c3a8258d10825516a0d0fe591b1cd23cedf5feedbadc9fa45b93e5f706 +size 3091662 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1111bd22ea4126aec955a3a211c63be07fb9da63 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0480f411e2b246cbd4b7cd5600fb1fceab070583c1a82cef0d75df2e6227857c +size 5325824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1893814a4d8649d3d3dca3d7c8c9ba9e90359b51 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_4f9febd8d1f222b8f798+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82ad6d40ce5fb57cd9843f5200bb7402ca48c7b325102e5d8b3f4903d0bf9494 +size 5492348 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..62e8531b63fbca93e4565bbe5bc845138d0ba90f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:341ec3a308108edc5b6d40f41ba7357b78ced94d0e4fead4dc848f5f08b025ed +size 2782804 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a27c370b9dc72c6008698d4008fb5bc232e8d90d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_53f20d124198545c96d2+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9249facb252aa3aa0e512ad34c5586a339d542618b8953db69182e128f6d44f +size 7588864 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d5eaa28cc777468bdc237528a51bd3eb1a9591eb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7b39b1035acb1d002e921f86caf315bb4ea10a30980cb4bcaf39ae5dd35706d +size 2766283 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..28042adf1ced6752c3f911a5ca1c73b4a7be40f7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_55d18f781d9212e2dfc6+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476ce0289f7530fb642f878a204b661e1bea11fe8fb77dfc2d09d2a08aded105 +size 7967744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..91386889e5c99d6b88bed3aa7aa2a3b166be35c3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0eff14a33281edae345d308b2aefe9a568dbf20e71eed5fa580adb036efe9980 +size 2475843 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..251d955e6d788fc2545f759efdfa979b7697c189 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:349489b596b9186de11be2dae318d49f9076cf90e7ea1f521599ccaea92cc800 +size 1823744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..d6271468cadef5a09f0b959df7f8f272f28fdeb2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_57df875f7fa16817b32e+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e603bfa7d0135d73105836d0e8c9e39837aa39c0b318ec55ecabf1c67ab3f58 +size 1934622 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..40ed621b5af1005e1c62de9c6162a8cf2abef8cb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97c0d480783bf946e64de828111c4db636ecf04f16cce831006fd60540ce9001 +size 3446477 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1e1e0f9945f5f0c693281ef5e321876718f3333b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5a4dba7b006e51d8f5aa+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:835641dc9968f4b74b63a60c29b440f431898a3bc74239df3f7b526f4c6e7432 +size 12381184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/model_index.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/model_index.json new file mode 100644 index 0000000000000000000000000000000000000000..9c4e759c9273460398e4f50355b6a7b42845634c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/model_index.json @@ -0,0 +1,42 @@ +{ + "_class_name": "StableDiffusionXLPipeline", + "_diffusers_version": "0.35.2", + "_name_or_path": "echarlaix/tiny-random-stable-diffusion-xl", + "feature_extractor": [ + null, + null + ], + "force_zeros_for_empty_prompt": true, + "image_encoder": [ + null, + null + ], + "scheduler": [ + "diffusers", + "EulerDiscreteScheduler" + ], + "text_encoder": [ + "transformers", + "CLIPTextModel" + ], + "text_encoder_2": [ + "transformers", + "CLIPTextModelWithProjection" + ], + "tokenizer": [ + "transformers", + "CLIPTokenizer" + ], + "tokenizer_2": [ + "transformers", + "CLIPTokenizer" + ], + "unet": [ + "diffusers", + "UNet2DConditionModel" + ], + "vae": [ + "diffusers", + "AutoencoderKL" + ] +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/scheduler/scheduler_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fe90d134cf0f4f483f797fdf8fd755db285fc743 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/scheduler/scheduler_config.json @@ -0,0 +1,21 @@ +{ + "_class_name": "EulerDiscreteScheduler", + "_diffusers_version": "0.35.2", + "beta_end": 0.012, + "beta_schedule": "scaled_linear", + "beta_start": 0.00085, + "final_sigmas_type": "zero", + "interpolation_type": "linear", + "num_train_timesteps": 1000, + "prediction_type": "epsilon", + "rescale_betas_zero_snr": false, + "sigma_max": null, + "sigma_min": null, + "steps_offset": 1, + "timestep_spacing": "leading", + "timestep_type": "discrete", + "trained_betas": null, + "use_beta_sigmas": false, + "use_exponential_sigmas": false, + "use_karras_sigmas": false +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..49a47e4e3fcd9bd026998834aa7a8992da33468c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder/config.json @@ -0,0 +1,46 @@ +{ + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dtype": "float32", + "eos_token_id": 2, + "export_model_type": "clip-text-model", + "hidden_act": "gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "clip-text-model", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "output_hidden_states": true, + "pad_token_id": 1, + "projection_dim": 32, + "return_dict": false, + "torchscript": true, + "transformers_version": "4.57.6", + "vocab_size": 1000 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..d6239aa60148e7e760e54cf96630427492f3c1ff --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7b7bd05229f33aab25467059ace4f6bbc9585df88a9541cbbef2dbc3f0b871 +size 813107 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder_2/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder_2/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0f4c3bb673702ded9a429289ed207f3228f69a87 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder_2/config.json @@ -0,0 +1,46 @@ +{ + "architectures": [ + "CLIPTextModelWithProjection" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dtype": "float32", + "eos_token_id": 2, + "export_model_type": "clip-text-with-projection", + "hidden_act": "gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "clip-text-with-projection", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "output_hidden_states": true, + "pad_token_id": 1, + "projection_dim": 32, + "return_dict": false, + "torchscript": true, + "transformers_version": "4.57.6", + "vocab_size": 1000 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder_2/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder_2/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..1941bc55ecde7dff3796666a30acb1f1c5a550a8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/text_encoder_2/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd0759d6f4027826a19e7e960f7533c33a6fd1085fd285f5fd2ff80df64bf190 +size 813299 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/merges.txt b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/merges.txt new file mode 100644 index 0000000000000000000000000000000000000000..e9193d6fc11f7b6e281b4686221363b6cdc4e576 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/merges.txt @@ -0,0 +1,647 @@ +#version: 0.2 +Ġ t +Ġt h +Ġ a +Ġth e +i n +Ġ o +Ġ , +Ġ s +e d +Ġ w +e r +Ġ . +Ġ i +r e +Ġ c +n d +Ġ f +Ġ b +a t +Ġo f +e r +e n +a r +o r +i t +Ġ p +Ġ h +Ġa nd +o n +in g +a n +r o +Ġ m +Ġ d +e s +Ġi n +o n +Ġt o +o u +i s +Ġ a +i c +Ġ T +a l +Ġ l +Ġ = +Ġ re +Ġ " +e s +Ġ S +a s +a l +i l +e l +i on +Ġ A +Ġ C +Ġ 1 +Ġ Ċ +u r +ĠT h +Ġ n +a s +Ġ @ +e c +o m +a c +Ġ e +Ġw as +Ġ M +o r +a n +a m +e n +o l +Ġ in +Ġ g +Ġ ' +Ġ B +l y +a t +i v +t s +ĠTh e +u s +- @ +Ġ@ -@ +i s +Ġ I +Ġw h +i g +Ġ H +Ġs t +o s +u n +t h +Ġ P +Ġw it +Ġth at +i r +Ġa s +e m +Ġo n +r a +Ġf or +Ġ R +e t +o w +Ġ 2 +i d +Ġ D +l e +Ġwit h +l a +en t +i m +Ġ F +e a +i on +Ġb y +Ġ ) +Ġ ( +Ġa l +Ġc on +en t +Ġ W +Ġi s +er e +Ġ G +Ġ N +Ġ L +Ġh a +er s +r i +t h +t ed +u c +Ġ J +Ġ1 9 +e v +u l +Ġ v +c e +at ion +ro m +Ġb e +Ġ E +i n +Ġth e +Ġf rom +Ġ O +t er +Ġp ro +Ġa r +a d +Ġc om +i c +a g +Ġh is +Ġs h +Ġa t +o v +i es +o o +p p +s t +c h +Ġ r +Ġ2 0 +a y +i f +Ġw ere +Ġc h +u t +s t +u t +d s +o p +u m +Ġi t +o c +t er +l e +ig h +u d +Ġe x +ion s +at e +it y +at ed +Ġ un +e p +q u +Ġn o +Ġ K +iv e +is t +Ġo n +am e +ou n +i r +a b +Ġ â +in g +Ġh e +l d +u g +ic h +Ġa n +e d +Ġ k +Ġâ Ģ +Ġha d +v e +a in +Ġs e +t ion +or e +re s +Ġwh ich +ĠI n +o d +th er +a k +Ġs p +a r +Ġ y +ĠC h +on g +Ġa c +es t +Ġ U +a p +f f +al ly +r it +ĠS t +u b +g e +b er +e t +Ġb e +e ar +Ġre c +er s +Ġf ir +o t +Ġar e +Ġa n +c h +o g +i a +es t +in e +il l +an d +e l +ar y +e w +i d +Ġf or +Ġ ; +Ġcom p +Ġ V +Ġin c +t r +Ġ20 0 +Ġthe ir +u s +Ġb ut +r an +ic al +Ġfir st +Ġd e +Ġin t +Ġ ro +s o +ĠâĢ ĵ +Ġno t +d ing +f ter +ur e +Ġp ar +Ġ : +i an +Ġt w +ou ld +Ġal so +Ġi ts +Ġw or +u m +Ġo r +os t +0 0 +ou r +ar d +Ġre s +m p +u e +Ġa b +is h +Ġcon t +Ġa d +ow n +al l +ou g +Ġh er +as t +Ġ en +om e +al l +d ed +o w +Ġha ve +Ġ us +ea r +ac k +d uc +i al +s s +en ts +a in +t ing +Ġon e +es s +Ġh as +igh t +a v +Ġe v +ou t +a y +en ce +Ġbe en +e w +Ġtw o +Ġc l +d er +im e +k s +es s +is h +. @ +Ġ@ .@ +Ġp la +Ġp l +Ġo r +u p +m ent +ur ing +ol l +ĠI n +Ġth is +Ġb ec +Ġcom m +Ġd is +at er +ag e +Ġa pp +ou s +e y +i l +p er +ĠA l +ion al +l ud +el y +t t +il e +i z +Ġ j +Ġwh o +Ġa g +i b +Ġthe y +f or +Ġo v +at h +e g +Ġs c +i p +Ġ20 1 +Ġ 3 +Ġp er +or y +Ġd es +id e +Ġs er +s e +ĠH e +la nd +at ions +r ic +i t +re s +er ed +Ġp re +ĠS h +an ce +or t +an t +, @ +Ġ@ ,@ +el l +Ġ Y +n ed +el l +it e +Ġinc lud +Ġre p +Ġa fter +Ġs uc +re e +an y +i m +or t +Ġ1 8 +Ġs u +ad e +ou r +ĠU n +ĠI t +i k +ĠM ar +em ber +Ġ 1 +e en +a nd +Ġs ec +ic e +Ġt ime +ĠA n +Ġint o +Ġf in +Ġo ther +Ġa tt +il l +re n +ac h +as s +er al +es e +s h +al s +it ion +oug h +l es +am p +Ġw ould +Ġm ore +ro ug +ri b +er y +ac e +Ġ A +Ġpla y +it ed +k ed +is t +i ed +Ġ 2 +as ed +ing s +an g +a m +i p +Ġb o +ab le +t y +Ġch ar +Ġc ent +et w +at es +ro p +Ġ I +u nd +ĠA m +c es +o in +Ġin ter +u p +c t +on e +Ġt ra +an t +ec t +Ġal l +e f +Ġcon s +ub l +n ing +an s +Ġf e +us t +Ġ 0 +Ġre m +as e +on g +Ġwh en +e b +ĠW h +Ġe ar +ev er +Ġov er +Ġk n +a us +Ġp os +a d +er m +Ġsh e +Ġ ra +Ġd uring +as on +v i +Ġex p +Ġl ea +Ġ el +Ġ 4 +Ġon ly +o nd +Ġd ec +Ġac c +Ġo ff +is s +Ġf l +ĠE n +o t +en s +os e +ak e +o m +Ġs ev +ac h +etw een +er n +Ġ 3 +Ġp r +Ġg ro +r uc +Ġd i +Ġ19 9 +ĠA r +Ġg ame +Ġh im +oo k +Ġ up +Ġab out +Ġre l +for m +Ġth ree +at t +ĠC om +Ġs a +ear s +Ġ 5 +r y +Ġi mp +Ġm ost +f er +Ġp res +Ġf il +Ġb etween +Ġbe g +p h +or s +Ġth an +Ġrec or +o b +er ic +at ing +Ġth roug +k ing +Ġo ut +Ġn um +oo d +oll ow +ac t +u il +Ġc re +ol og +at ional +Ġpro duc +Ġwh ile +Ġl ater +Ġw rit +e x +Ġst ar +Ġsp ec +e e +ish ed +Ġre g +is ion +ou th +Ġre le +Ġa ss +Ġse ason +Ġm ade +il y +r u +o y +t ur +t e +Ġ qu +Ġm ov +ur y +ĠAm eric +em ent +c c +ou nd +Ġl ar +Ġfor m +ec t +Ġde f +Ġm us +ĠP ar +Ġm e +Ġs ub +w ay +o p +o h +el d +i e +em p +am es +er n +Ġn or +iv ed +ev el +Ġsuc h +ar ds +Ġin d +ik e +Ġg en +er t +Ġy ear +Ġus ed +Ġn ew +Ġ 5 +Ġal b +s p +y p +Ġwit h +Ġwh ere +ic s +ĠTh is +Ġthe m +w n diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/special_tokens_map.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..2c2130b544c0c5a72d5d00da071ba130a9800fb2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|endoftext|>", + "unk_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/tokenizer_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1afa8218eecb1e24f97a91b510e36bc35d5feec4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/tokenizer_config.json @@ -0,0 +1,31 @@ +{ + "add_prefix_space": false, + "added_tokens_decoder": { + "0": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": true, + "do_lower_case": true, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 77, + "pad_token": "<|endoftext|>", + "tokenizer_class": "CLIPTokenizer", + "unk_token": "<|endoftext|>" +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/vocab.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/vocab.json new file mode 100644 index 0000000000000000000000000000000000000000..609c08ebb708079189a79c6964c3495e36b26f41 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer/vocab.json @@ -0,0 +1,1002 @@ +{ + "!": 2, + "!": 345, + "\"": 3, + "\"": 344, + "#": 4, + "#": 325, + "$": 5, + "$": 348, + "%": 6, + "%": 351, + "&": 7, + "&": 352, + "'": 8, + "'": 296, + "(": 9, + "(": 318, + ")": 10, + ")": 330, + "*": 11, + "*": 327, + "+": 12, + "+": 341, + ",": 13, + ",": 279, + ",@": 754, + "-": 14, + "-": 276, + "-@": 439, + ".": 15, + ".": 253, + ".@": 695, + "/": 16, + "/": 350, + "0": 17, + "00": 647, + "0": 216, + "1": 18, + "1": 222, + "2": 19, + "2": 231, + "3": 20, + "3": 243, + "4": 21, + "4": 233, + "5": 22, + "5": 240, + "6": 23, + "6": 226, + "7": 24, + "7": 215, + "8": 25, + "8": 236, + "9": 26, + "9": 242, + ":": 27, + ":": 353, + ";": 28, + ";": 317, + "<": 29, + "<": 340, + "<|endoftext|>": 1, + "<|startoftext|>": 0, + "=": 30, + "=": 342, + ">": 31, + ">": 300, + "?": 32, + "?": 346, + "@": 33, + "@": 320, + "A": 34, + "A": 227, + "B": 35, + "B": 258, + "C": 36, + "C": 239, + "D": 37, + "D": 255, + "E": 38, + "E": 246, + "F": 39, + "F": 213, + "G": 40, + "G": 283, + "H": 41, + "H": 219, + "I": 42, + "I": 237, + "J": 43, + "J": 251, + "K": 44, + "K": 254, + "L": 45, + "L": 218, + "M": 46, + "M": 234, + "N": 47, + "N": 238, + "O": 48, + "O": 265, + "P": 49, + "P": 245, + "Q": 50, + "Q": 309, + "R": 51, + "R": 264, + "S": 52, + "S": 230, + "T": 53, + "T": 235, + "U": 54, + "U": 268, + "V": 55, + "V": 248, + "W": 56, + "W": 274, + "X": 57, + "X": 263, + "Y": 58, + "Y": 310, + "Z": 59, + "Z": 207, + "[": 60, + "[": 270, + "\\": 61, + "\\": 338, + "]": 62, + "]": 289, + "^": 63, + "^": 331, + "_": 64, + "_": 334, + "`": 65, + "`": 347, + "a": 66, + "a": 197, + "ab": 555, + "able": 820, + "ac": 420, + "ace": 806, + "ach": 791, + "ach": 885, + "ack": 670, + "act": 929, + "ad": 508, + "ad": 860, + "ade": 771, + "ag": 511, + "age": 710, + "ain": 568, + "ain": 675, + "ak": 577, + "ake": 882, + "al": 397, + "al": 405, + "all": 664, + "all": 658, + "ally": 588, + "als": 796, + "am": 426, + "am": 817, + "ame": 552, + "ames": 976, + "amp": 800, + "an": 384, + "an": 425, + "ance": 751, + "and": 609, + "and": 780, + "ang": 816, + "ans": 844, + "ant": 837, + "ant": 753, + "any": 766, + "ap": 586, + "ar": 376, + "ar": 579, + "ard": 649, + "ards": 982, + "ary": 611, + "as": 416, + "as": 404, + "ase": 849, + "ased": 814, + "ason": 865, + "ass": 792, + "ast": 661, + "at": 372, + "at": 434, + "ate": 541, + "ated": 543, + "ater": 709, + "ates": 825, + "ath": 730, + "ating": 922, + "ation": 497, + "ational": 933, + "ations": 744, + "att": 903, + "aus": 858, + "av": 681, + "ay": 684, + "ay": 523, + "b": 67, + "b": 212, + "ber": 593, + "c": 68, + "c": 224, + "cc": 960, + "ce": 496, + "ces": 830, + "ch": 520, + "ch": 603, + "ct": 834, + "d": 69, + "d": 196, + "ded": 665, + "der": 690, + "ding": 633, + "ds": 530, + "duc": 671, + "e": 70, + "e": 195, + "ea": 471, + "ear": 596, + "ear": 669, + "ears": 906, + "eb": 852, + "ec": 418, + "ect": 838, + "ect": 964, + "ed": 563, + "ed": 362, + "ee": 941, + "een": 779, + "ef": 840, + "eg": 731, + "el": 407, + "el": 610, + "eld": 973, + "ell": 759, + "ell": 756, + "ely": 719, + "em": 455, + "ember": 777, + "ement": 959, + "emp": 975, + "en": 375, + "en": 427, + "ence": 685, + "ens": 880, + "ent": 478, + "ent": 468, + "ents": 674, + "ep": 545, + "er": 364, + "er": 374, + "eral": 793, + "ere": 481, + "ered": 748, + "eric": 921, + "erm": 861, + "ern": 887, + "ern": 977, + "ers": 598, + "ers": 486, + "ert": 986, + "ery": 805, + "es": 402, + "es": 388, + "ese": 794, + "ess": 678, + "ess": 693, + "est": 606, + "est": 584, + "et": 460, + "et": 594, + "etw": 824, + "etween": 886, + "ev": 493, + "evel": 980, + "ever": 855, + "ew": 687, + "ew": 612, + "ex": 938, + "ey": 713, + "f": 71, + "f": 209, + "fer": 911, + "ff": 587, + "for": 728, + "form": 901, + "fter": 634, + "g": 72, + "g": 214, + "ge": 592, + "h": 73, + "h": 203, + "i": 74, + "i": 205, + "ia": 605, + "ial": 672, + "ian": 638, + "ib": 726, + "ic": 395, + "ic": 510, + "ical": 625, + "ice": 782, + "ich": 561, + "ics": 996, + "id": 463, + "id": 613, + "ide": 739, + "ie": 974, + "ied": 812, + "ies": 516, + "if": 524, + "ig": 444, + "igh": 537, + "ight": 680, + "ik": 775, + "ike": 984, + "il": 406, + "il": 714, + "ile": 721, + "ill": 608, + "ill": 789, + "ily": 950, + "im": 469, + "im": 767, + "ime": 691, + "in": 358, + "in": 501, + "ine": 607, + "ing": 557, + "ing": 383, + "ings": 815, + "ion": 472, + "ion": 408, + "ional": 717, + "ions": 540, + "ip": 733, + "ip": 818, + "ir": 453, + "ir": 554, + "is": 393, + "is": 441, + "ish": 694, + "ish": 654, + "ished": 942, + "ision": 944, + "iss": 876, + "ist": 550, + "ist": 811, + "it": 378, + "it": 746, + "ite": 760, + "ited": 809, + "ition": 797, + "ity": 542, + "iv": 435, + "ive": 549, + "ived": 979, + "iz": 722, + "j": 75, + "j": 288, + "k": 76, + "k": 210, + "ked": 810, + "king": 924, + "ks": 692, + "l": 77, + "l": 201, + "la": 467, + "land": 743, + "ld": 559, + "le": 536, + "le": 465, + "les": 799, + "lud": 718, + "ly": 433, + "m": 78, + "m": 202, + "ment": 701, + "mp": 651, + "n": 79, + "n": 199, + "nd": 369, + "ned": 758, + "ning": 843, + "o": 80, + "o": 198, + "ob": 920, + "oc": 534, + "od": 575, + "og": 604, + "oh": 972, + "oin": 831, + "ol": 428, + "oll": 703, + "ollow": 928, + "olog": 932, + "om": 419, + "om": 883, + "ome": 663, + "on": 382, + "on": 390, + "ond": 872, + "one": 835, + "ong": 850, + "ong": 582, + "oo": 517, + "ood": 927, + "ook": 897, + "op": 531, + "op": 971, + "or": 377, + "or": 424, + "ore": 571, + "ors": 917, + "ort": 768, + "ort": 752, + "ory": 737, + "os": 447, + "ose": 881, + "ost": 646, + "ot": 600, + "ot": 879, + "ou": 392, + "oug": 659, + "ough": 798, + "ould": 640, + "oun": 553, + "ound": 961, + "our": 648, + "our": 772, + "ous": 712, + "out": 683, + "outh": 945, + "ov": 515, + "ow": 461, + "ow": 666, + "own": 657, + "oy": 952, + "p": 81, + "p": 217, + "per": 715, + "ph": 916, + "pp": 518, + "q": 82, + "q": 280, + "qu": 546, + "r": 83, + "r": 204, + "ra": 457, + "ran": 624, + "re": 367, + "ree": 765, + "ren": 790, + "res": 572, + "res": 747, + "ri": 487, + "rib": 804, + "ric": 745, + "rit": 589, + "ro": 385, + "rom": 498, + "rop": 826, + "roug": 803, + "ru": 951, + "ruc": 891, + "ry": 908, + "s": 84, + "s": 206, + "se": 741, + "sh": 795, + "so": 630, + "sp": 992, + "ss": 673, + "st": 519, + "st": 528, + "t": 85, + "t": 208, + "te": 954, + "ted": 489, + "ter": 535, + "ter": 505, + "th": 449, + "th": 488, + "ther": 576, + "ting": 676, + "tion": 570, + "tr": 619, + "ts": 436, + "tt": 720, + "tur": 953, + "ty": 821, + "u": 86, + "u": 229, + "ub": 591, + "ubl": 842, + "uc": 490, + "ud": 538, + "ue": 652, + "ug": 560, + "uil": 930, + "ul": 494, + "um": 532, + "um": 644, + "un": 448, + "und": 828, + "up": 833, + "up": 700, + "ur": 413, + "ure": 635, + "uring": 702, + "ury": 957, + "us": 438, + "us": 622, + "ust": 846, + "ut": 529, + "ut": 527, + "v": 87, + "v": 232, + "ve": 567, + "vi": 866, + "w": 88, + "w": 250, + "way": 970, + "wn": 999, + "x": 89, + "x": 269, + "y": 90, + "y": 211, + "yp": 993, + "z": 91, + "z": 228, + "|": 92, + "|": 304, + "}": 93, + "}": 336, + "~": 94, + "~": 343, + "¡": 95, + "¡": 220, + "¢": 96, + "¢": 306, + "£": 97, + "£": 323, + "¤": 98, + "¤": 292, + "¥": 99, + "¥": 339, + "¦": 100, + "¦": 303, + "§": 101, + "§": 275, + "¨": 102, + "¨": 282, + "©": 103, + "©": 259, + "ª": 104, + "ª": 286, + "«": 105, + "«": 266, + "¬": 106, + "¬": 319, + "®": 107, + "®": 329, + "¯": 108, + "¯": 287, + "°": 109, + "°": 298, + "±": 110, + "±": 200, + "²": 111, + "²": 284, + "³": 112, + "³": 272, + "´": 113, + "´": 307, + "µ": 114, + "µ": 261, + "¶": 115, + "¶": 301, + "·": 116, + "·": 326, + "¸": 117, + "¸": 257, + "¹": 118, + "¹": 241, + "º": 119, + "º": 260, + "»": 120, + "»": 247, + "¼": 121, + "¼": 305, + "½": 122, + "½": 294, + "¾": 123, + "¾": 316, + "¿": 124, + "¿": 271, + "Â": 125, + "Ã": 126, + "Ä": 127, + "Å": 128, + "Æ": 129, + "Ç": 130, + "È": 131, + "É": 132, + "Ê": 133, + "Ë": 134, + "Ì": 135, + "Í": 136, + "Î": 137, + "Ï": 138, + "Ð": 139, + "Ñ": 140, + "Ö": 141, + "×": 142, + "Ø": 143, + "Ù": 144, + "Ü": 145, + "à": 146, + "á": 147, + "â": 148, + "ã": 149, + "ä": 150, + "å": 151, + "æ": 152, + "ç": 153, + "è": 154, + "é": 155, + "ë": 156, + "ì": 157, + "ï": 158, + "Ċ": 159, + "Ċ": 349, + "Ġ": 160, + "Ġ\"": 401, + "Ġ'": 431, + "Ġ(": 475, + "Ġ)": 474, + "Ġ,": 360, + "Ġ.": 365, + "Ġ0": 847, + "Ġ1": 411, + "Ġ18": 769, + "Ġ19": 492, + "Ġ199": 893, + "Ġ1": 778, + "Ġ2": 462, + "Ġ20": 522, + "Ġ200": 620, + "Ġ201": 734, + "Ġ2": 813, + "Ġ3": 735, + "Ġ3": 888, + "Ġ4": 870, + "Ġ5": 907, + "Ġ5": 990, + "Ġ:": 637, + "Ġ;": 615, + "Ġ": 333, + "Ġ=": 399, + "Ġ@": 417, + "Ġ@,@": 755, + "Ġ@-@": 440, + "Ġ@.@": 696, + "ĠA": 409, + "ĠA": 807, + "ĠAl": 716, + "ĠAm": 829, + "ĠAmeric": 958, + "ĠAn": 784, + "ĠAr": 894, + "ĠB": 432, + "ĠC": 410, + "ĠCh": 581, + "ĠCom": 904, + "ĠD": 464, + "ĠE": 500, + "ĠEn": 878, + "ĠF": 470, + "ĠG": 482, + "ĠH": 445, + "ĠHe": 742, + "ĠI": 442, + "ĠI": 827, + "ĠIn": 704, + "ĠIn": 574, + "ĠIt": 774, + "ĠJ": 491, + "ĠK": 548, + "ĠL": 484, + "ĠM": 423, + "ĠMar": 776, + "ĠN": 483, + "ĠO": 504, + "ĠP": 450, + "ĠPar": 967, + "ĠR": 459, + "ĠS": 403, + "ĠSh": 750, + "ĠSt": 590, + "ĠT": 396, + "ĠTh": 414, + "ĠThe": 437, + "ĠThis": 997, + "ĠU": 585, + "ĠUn": 773, + "ĠV": 617, + "ĠW": 479, + "ĠWh": 853, + "ĠY": 757, + "Ġa": 356, + "Ġa": 394, + "Ġab": 653, + "Ġabout": 899, + "Ġac": 583, + "Ġacc": 874, + "Ġad": 656, + "Ġafter": 763, + "Ġag": 725, + "Ġal": 476, + "Ġalb": 991, + "Ġall": 839, + "Ġalso": 641, + "Ġan": 602, + "Ġan": 562, + "Ġand": 381, + "Ġapp": 711, + "Ġar": 507, + "Ġare": 601, + "Ġas": 454, + "Ġass": 947, + "Ġat": 514, + "Ġatt": 788, + "Ġb": 371, + "Ġbe": 499, + "Ġbe": 595, + "Ġbec": 706, + "Ġbeen": 686, + "Ġbeg": 915, + "Ġbetween": 914, + "Ġbo": 819, + "Ġbut": 623, + "Ġby": 473, + "Ġc": 368, + "Ġcent": 823, + "Ġch": 526, + "Ġchar": 822, + "Ġcl": 689, + "Ġcom": 509, + "Ġcomm": 707, + "Ġcomp": 616, + "Ġcon": 477, + "Ġcons": 841, + "Ġcont": 655, + "Ġcre": 931, + "Ġd": 387, + "Ġde": 627, + "Ġdec": 873, + "Ġdef": 965, + "Ġdes": 738, + "Ġdi": 892, + "Ġdis": 708, + "Ġduring": 864, + "Ġe": 421, + "Ġear": 854, + "Ġel": 869, + "Ġen": 662, + "Ġev": 682, + "Ġex": 539, + "Ġexp": 867, + "Ġf": 370, + "Ġfe": 845, + "Ġfil": 913, + "Ġfin": 786, + "Ġfir": 599, + "Ġfirst": 626, + "Ġfl": 877, + "Ġfor": 614, + "Ġfor": 458, + "Ġform": 963, + "Ġfrom": 503, + "Ġg": 430, + "Ġgame": 895, + "Ġgen": 985, + "Ġgro": 890, + "Ġh": 380, + "Ġha": 485, + "Ġhad": 566, + "Ġhas": 679, + "Ġhave": 667, + "Ġhe": 558, + "Ġher": 660, + "Ġhim": 896, + "Ġhis": 512, + "Ġi": 366, + "Ġimp": 909, + "Ġin": 429, + "Ġin": 389, + "Ġinc": 618, + "Ġinclud": 761, + "Ġind": 983, + "Ġint": 628, + "Ġinter": 832, + "Ġinto": 785, + "Ġis": 480, + "Ġit": 533, + "Ġits": 642, + "Ġj": 723, + "Ġk": 564, + "Ġkn": 857, + "Ġl": 398, + "Ġlar": 962, + "Ġlater": 936, + "Ġlea": 868, + "Ġm": 386, + "Ġmade": 949, + "Ġme": 968, + "Ġmore": 802, + "Ġmost": 910, + "Ġmov": 956, + "Ġmus": 966, + "Ġn": 415, + "Ġnew": 989, + "Ġno": 547, + "Ġnor": 978, + "Ġnot": 632, + "Ġnum": 926, + "Ġo": 359, + "Ġof": 373, + "Ġoff": 875, + "Ġon": 551, + "Ġon": 456, + "Ġone": 677, + "Ġonly": 871, + "Ġor": 699, + "Ġor": 645, + "Ġother": 787, + "Ġout": 925, + "Ġov": 729, + "Ġover": 856, + "Ġp": 379, + "Ġpar": 636, + "Ġper": 736, + "Ġpl": 698, + "Ġpla": 697, + "Ġplay": 808, + "Ġpos": 859, + "Ġpr": 889, + "Ġpre": 749, + "Ġpres": 912, + "Ġpro": 506, + "Ġproduc": 934, + "Ġqu": 955, + "Ġr": 521, + "Ġra": 863, + "Ġre": 400, + "Ġrec": 597, + "Ġrecor": 919, + "Ġreg": 943, + "Ġrel": 900, + "Ġrele": 946, + "Ġrem": 848, + "Ġrep": 762, + "Ġres": 650, + "Ġro": 629, + "Ġs": 361, + "Ġsa": 905, + "Ġsc": 732, + "Ġse": 569, + "Ġseason": 948, + "Ġsec": 781, + "Ġser": 740, + "Ġsev": 884, + "Ġsh": 513, + "Ġshe": 862, + "Ġsp": 578, + "Ġspec": 940, + "Ġst": 446, + "Ġstar": 939, + "Ġsu": 770, + "Ġsub": 969, + "Ġsuc": 764, + "Ġsuch": 981, + "Ġt": 354, + "Ġth": 355, + "Ġthan": 918, + "Ġthat": 452, + "Ġthe": 502, + "Ġthe": 357, + "Ġtheir": 621, + "Ġthem": 998, + "Ġthey": 727, + "Ġthis": 705, + "Ġthree": 902, + "Ġthroug": 923, + "Ġtime": 783, + "Ġto": 391, + "Ġtra": 836, + "Ġtw": 639, + "Ġtwo": 688, + "Ġun": 544, + "Ġup": 898, + "Ġus": 668, + "Ġused": 988, + "Ġv": 495, + "Ġw": 363, + "Ġwas": 422, + "Ġwere": 525, + "Ġwh": 443, + "Ġwhen": 851, + "Ġwhere": 995, + "Ġwhich": 573, + "Ġwhile": 935, + "Ġwho": 724, + "Ġwit": 451, + "Ġwith": 994, + "Ġwith": 466, + "Ġwor": 643, + "Ġwould": 801, + "Ġwrit": 937, + "Ġy": 580, + "Ġyear": 987, + "Ġâ": 556, + "ĠâĢ": 565, + "ĠâĢĵ": 631, + "ĠĊ": 412, + "Ģ": 161, + "Ģ": 223, + "ģ": 162, + "ģ": 273, + "Ĥ": 163, + "Ĥ": 262, + "ĥ": 164, + "ĥ": 337, + "Ħ": 165, + "Ħ": 278, + "ħ": 166, + "ħ": 281, + "Ĩ": 167, + "Ĩ": 308, + "ĩ": 168, + "ĩ": 225, + "Ī": 169, + "Ī": 221, + "ī": 170, + "ī": 244, + "Ĭ": 171, + "Ĭ": 315, + "ĭ": 172, + "ĭ": 321, + "Į": 173, + "Į": 324, + "į": 174, + "į": 302, + "İ": 175, + "İ": 249, + "ı": 176, + "ı": 332, + "IJ": 177, + "IJ": 295, + "ij": 178, + "ij": 313, + "Ĵ": 179, + "Ĵ": 328, + "ĵ": 180, + "ĵ": 312, + "Ķ": 181, + "Ķ": 256, + "ķ": 182, + "ķ": 314, + "ĸ": 183, + "ĸ": 277, + "Ĺ": 184, + "Ĺ": 322, + "ĺ": 185, + "ĺ": 285, + "Ļ": 186, + "Ļ": 267, + "ļ": 187, + "ļ": 290, + "Ľ": 188, + "Ľ": 311, + "ľ": 189, + "ľ": 299, + "Ŀ": 190, + "Ŀ": 291, + "ŀ": 191, + "ŀ": 293, + "Ł": 192, + "Ł": 335, + "ł": 193, + "ł": 252, + "Ń": 194, + "Ń": 297 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/merges.txt b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/merges.txt new file mode 100644 index 0000000000000000000000000000000000000000..e9193d6fc11f7b6e281b4686221363b6cdc4e576 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/merges.txt @@ -0,0 +1,647 @@ +#version: 0.2 +Ġ t +Ġt h +Ġ a +Ġth e +i n +Ġ o +Ġ , +Ġ s +e d +Ġ w +e r +Ġ . +Ġ i +r e +Ġ c +n d +Ġ f +Ġ b +a t +Ġo f +e r +e n +a r +o r +i t +Ġ p +Ġ h +Ġa nd +o n +in g +a n +r o +Ġ m +Ġ d +e s +Ġi n +o n +Ġt o +o u +i s +Ġ a +i c +Ġ T +a l +Ġ l +Ġ = +Ġ re +Ġ " +e s +Ġ S +a s +a l +i l +e l +i on +Ġ A +Ġ C +Ġ 1 +Ġ Ċ +u r +ĠT h +Ġ n +a s +Ġ @ +e c +o m +a c +Ġ e +Ġw as +Ġ M +o r +a n +a m +e n +o l +Ġ in +Ġ g +Ġ ' +Ġ B +l y +a t +i v +t s +ĠTh e +u s +- @ +Ġ@ -@ +i s +Ġ I +Ġw h +i g +Ġ H +Ġs t +o s +u n +t h +Ġ P +Ġw it +Ġth at +i r +Ġa s +e m +Ġo n +r a +Ġf or +Ġ R +e t +o w +Ġ 2 +i d +Ġ D +l e +Ġwit h +l a +en t +i m +Ġ F +e a +i on +Ġb y +Ġ ) +Ġ ( +Ġa l +Ġc on +en t +Ġ W +Ġi s +er e +Ġ G +Ġ N +Ġ L +Ġh a +er s +r i +t h +t ed +u c +Ġ J +Ġ1 9 +e v +u l +Ġ v +c e +at ion +ro m +Ġb e +Ġ E +i n +Ġth e +Ġf rom +Ġ O +t er +Ġp ro +Ġa r +a d +Ġc om +i c +a g +Ġh is +Ġs h +Ġa t +o v +i es +o o +p p +s t +c h +Ġ r +Ġ2 0 +a y +i f +Ġw ere +Ġc h +u t +s t +u t +d s +o p +u m +Ġi t +o c +t er +l e +ig h +u d +Ġe x +ion s +at e +it y +at ed +Ġ un +e p +q u +Ġn o +Ġ K +iv e +is t +Ġo n +am e +ou n +i r +a b +Ġ â +in g +Ġh e +l d +u g +ic h +Ġa n +e d +Ġ k +Ġâ Ģ +Ġha d +v e +a in +Ġs e +t ion +or e +re s +Ġwh ich +ĠI n +o d +th er +a k +Ġs p +a r +Ġ y +ĠC h +on g +Ġa c +es t +Ġ U +a p +f f +al ly +r it +ĠS t +u b +g e +b er +e t +Ġb e +e ar +Ġre c +er s +Ġf ir +o t +Ġar e +Ġa n +c h +o g +i a +es t +in e +il l +an d +e l +ar y +e w +i d +Ġf or +Ġ ; +Ġcom p +Ġ V +Ġin c +t r +Ġ20 0 +Ġthe ir +u s +Ġb ut +r an +ic al +Ġfir st +Ġd e +Ġin t +Ġ ro +s o +ĠâĢ ĵ +Ġno t +d ing +f ter +ur e +Ġp ar +Ġ : +i an +Ġt w +ou ld +Ġal so +Ġi ts +Ġw or +u m +Ġo r +os t +0 0 +ou r +ar d +Ġre s +m p +u e +Ġa b +is h +Ġcon t +Ġa d +ow n +al l +ou g +Ġh er +as t +Ġ en +om e +al l +d ed +o w +Ġha ve +Ġ us +ea r +ac k +d uc +i al +s s +en ts +a in +t ing +Ġon e +es s +Ġh as +igh t +a v +Ġe v +ou t +a y +en ce +Ġbe en +e w +Ġtw o +Ġc l +d er +im e +k s +es s +is h +. @ +Ġ@ .@ +Ġp la +Ġp l +Ġo r +u p +m ent +ur ing +ol l +ĠI n +Ġth is +Ġb ec +Ġcom m +Ġd is +at er +ag e +Ġa pp +ou s +e y +i l +p er +ĠA l +ion al +l ud +el y +t t +il e +i z +Ġ j +Ġwh o +Ġa g +i b +Ġthe y +f or +Ġo v +at h +e g +Ġs c +i p +Ġ20 1 +Ġ 3 +Ġp er +or y +Ġd es +id e +Ġs er +s e +ĠH e +la nd +at ions +r ic +i t +re s +er ed +Ġp re +ĠS h +an ce +or t +an t +, @ +Ġ@ ,@ +el l +Ġ Y +n ed +el l +it e +Ġinc lud +Ġre p +Ġa fter +Ġs uc +re e +an y +i m +or t +Ġ1 8 +Ġs u +ad e +ou r +ĠU n +ĠI t +i k +ĠM ar +em ber +Ġ 1 +e en +a nd +Ġs ec +ic e +Ġt ime +ĠA n +Ġint o +Ġf in +Ġo ther +Ġa tt +il l +re n +ac h +as s +er al +es e +s h +al s +it ion +oug h +l es +am p +Ġw ould +Ġm ore +ro ug +ri b +er y +ac e +Ġ A +Ġpla y +it ed +k ed +is t +i ed +Ġ 2 +as ed +ing s +an g +a m +i p +Ġb o +ab le +t y +Ġch ar +Ġc ent +et w +at es +ro p +Ġ I +u nd +ĠA m +c es +o in +Ġin ter +u p +c t +on e +Ġt ra +an t +ec t +Ġal l +e f +Ġcon s +ub l +n ing +an s +Ġf e +us t +Ġ 0 +Ġre m +as e +on g +Ġwh en +e b +ĠW h +Ġe ar +ev er +Ġov er +Ġk n +a us +Ġp os +a d +er m +Ġsh e +Ġ ra +Ġd uring +as on +v i +Ġex p +Ġl ea +Ġ el +Ġ 4 +Ġon ly +o nd +Ġd ec +Ġac c +Ġo ff +is s +Ġf l +ĠE n +o t +en s +os e +ak e +o m +Ġs ev +ac h +etw een +er n +Ġ 3 +Ġp r +Ġg ro +r uc +Ġd i +Ġ19 9 +ĠA r +Ġg ame +Ġh im +oo k +Ġ up +Ġab out +Ġre l +for m +Ġth ree +at t +ĠC om +Ġs a +ear s +Ġ 5 +r y +Ġi mp +Ġm ost +f er +Ġp res +Ġf il +Ġb etween +Ġbe g +p h +or s +Ġth an +Ġrec or +o b +er ic +at ing +Ġth roug +k ing +Ġo ut +Ġn um +oo d +oll ow +ac t +u il +Ġc re +ol og +at ional +Ġpro duc +Ġwh ile +Ġl ater +Ġw rit +e x +Ġst ar +Ġsp ec +e e +ish ed +Ġre g +is ion +ou th +Ġre le +Ġa ss +Ġse ason +Ġm ade +il y +r u +o y +t ur +t e +Ġ qu +Ġm ov +ur y +ĠAm eric +em ent +c c +ou nd +Ġl ar +Ġfor m +ec t +Ġde f +Ġm us +ĠP ar +Ġm e +Ġs ub +w ay +o p +o h +el d +i e +em p +am es +er n +Ġn or +iv ed +ev el +Ġsuc h +ar ds +Ġin d +ik e +Ġg en +er t +Ġy ear +Ġus ed +Ġn ew +Ġ 5 +Ġal b +s p +y p +Ġwit h +Ġwh ere +ic s +ĠTh is +Ġthe m +w n diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/special_tokens_map.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..2c2130b544c0c5a72d5d00da071ba130a9800fb2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|endoftext|>", + "unk_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/tokenizer_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..1afa8218eecb1e24f97a91b510e36bc35d5feec4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/tokenizer_config.json @@ -0,0 +1,31 @@ +{ + "add_prefix_space": false, + "added_tokens_decoder": { + "0": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": true, + "do_lower_case": true, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 77, + "pad_token": "<|endoftext|>", + "tokenizer_class": "CLIPTokenizer", + "unk_token": "<|endoftext|>" +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/vocab.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/vocab.json new file mode 100644 index 0000000000000000000000000000000000000000..609c08ebb708079189a79c6964c3495e36b26f41 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/tokenizer_2/vocab.json @@ -0,0 +1,1002 @@ +{ + "!": 2, + "!": 345, + "\"": 3, + "\"": 344, + "#": 4, + "#": 325, + "$": 5, + "$": 348, + "%": 6, + "%": 351, + "&": 7, + "&": 352, + "'": 8, + "'": 296, + "(": 9, + "(": 318, + ")": 10, + ")": 330, + "*": 11, + "*": 327, + "+": 12, + "+": 341, + ",": 13, + ",": 279, + ",@": 754, + "-": 14, + "-": 276, + "-@": 439, + ".": 15, + ".": 253, + ".@": 695, + "/": 16, + "/": 350, + "0": 17, + "00": 647, + "0": 216, + "1": 18, + "1": 222, + "2": 19, + "2": 231, + "3": 20, + "3": 243, + "4": 21, + "4": 233, + "5": 22, + "5": 240, + "6": 23, + "6": 226, + "7": 24, + "7": 215, + "8": 25, + "8": 236, + "9": 26, + "9": 242, + ":": 27, + ":": 353, + ";": 28, + ";": 317, + "<": 29, + "<": 340, + "<|endoftext|>": 1, + "<|startoftext|>": 0, + "=": 30, + "=": 342, + ">": 31, + ">": 300, + "?": 32, + "?": 346, + "@": 33, + "@": 320, + "A": 34, + "A": 227, + "B": 35, + "B": 258, + "C": 36, + "C": 239, + "D": 37, + "D": 255, + "E": 38, + "E": 246, + "F": 39, + "F": 213, + "G": 40, + "G": 283, + "H": 41, + "H": 219, + "I": 42, + "I": 237, + "J": 43, + "J": 251, + "K": 44, + "K": 254, + "L": 45, + "L": 218, + "M": 46, + "M": 234, + "N": 47, + "N": 238, + "O": 48, + "O": 265, + "P": 49, + "P": 245, + "Q": 50, + "Q": 309, + "R": 51, + "R": 264, + "S": 52, + "S": 230, + "T": 53, + "T": 235, + "U": 54, + "U": 268, + "V": 55, + "V": 248, + "W": 56, + "W": 274, + "X": 57, + "X": 263, + "Y": 58, + "Y": 310, + "Z": 59, + "Z": 207, + "[": 60, + "[": 270, + "\\": 61, + "\\": 338, + "]": 62, + "]": 289, + "^": 63, + "^": 331, + "_": 64, + "_": 334, + "`": 65, + "`": 347, + "a": 66, + "a": 197, + "ab": 555, + "able": 820, + "ac": 420, + "ace": 806, + "ach": 791, + "ach": 885, + "ack": 670, + "act": 929, + "ad": 508, + "ad": 860, + "ade": 771, + "ag": 511, + "age": 710, + "ain": 568, + "ain": 675, + "ak": 577, + "ake": 882, + "al": 397, + "al": 405, + "all": 664, + "all": 658, + "ally": 588, + "als": 796, + "am": 426, + "am": 817, + "ame": 552, + "ames": 976, + "amp": 800, + "an": 384, + "an": 425, + "ance": 751, + "and": 609, + "and": 780, + "ang": 816, + "ans": 844, + "ant": 837, + "ant": 753, + "any": 766, + "ap": 586, + "ar": 376, + "ar": 579, + "ard": 649, + "ards": 982, + "ary": 611, + "as": 416, + "as": 404, + "ase": 849, + "ased": 814, + "ason": 865, + "ass": 792, + "ast": 661, + "at": 372, + "at": 434, + "ate": 541, + "ated": 543, + "ater": 709, + "ates": 825, + "ath": 730, + "ating": 922, + "ation": 497, + "ational": 933, + "ations": 744, + "att": 903, + "aus": 858, + "av": 681, + "ay": 684, + "ay": 523, + "b": 67, + "b": 212, + "ber": 593, + "c": 68, + "c": 224, + "cc": 960, + "ce": 496, + "ces": 830, + "ch": 520, + "ch": 603, + "ct": 834, + "d": 69, + "d": 196, + "ded": 665, + "der": 690, + "ding": 633, + "ds": 530, + "duc": 671, + "e": 70, + "e": 195, + "ea": 471, + "ear": 596, + "ear": 669, + "ears": 906, + "eb": 852, + "ec": 418, + "ect": 838, + "ect": 964, + "ed": 563, + "ed": 362, + "ee": 941, + "een": 779, + "ef": 840, + "eg": 731, + "el": 407, + "el": 610, + "eld": 973, + "ell": 759, + "ell": 756, + "ely": 719, + "em": 455, + "ember": 777, + "ement": 959, + "emp": 975, + "en": 375, + "en": 427, + "ence": 685, + "ens": 880, + "ent": 478, + "ent": 468, + "ents": 674, + "ep": 545, + "er": 364, + "er": 374, + "eral": 793, + "ere": 481, + "ered": 748, + "eric": 921, + "erm": 861, + "ern": 887, + "ern": 977, + "ers": 598, + "ers": 486, + "ert": 986, + "ery": 805, + "es": 402, + "es": 388, + "ese": 794, + "ess": 678, + "ess": 693, + "est": 606, + "est": 584, + "et": 460, + "et": 594, + "etw": 824, + "etween": 886, + "ev": 493, + "evel": 980, + "ever": 855, + "ew": 687, + "ew": 612, + "ex": 938, + "ey": 713, + "f": 71, + "f": 209, + "fer": 911, + "ff": 587, + "for": 728, + "form": 901, + "fter": 634, + "g": 72, + "g": 214, + "ge": 592, + "h": 73, + "h": 203, + "i": 74, + "i": 205, + "ia": 605, + "ial": 672, + "ian": 638, + "ib": 726, + "ic": 395, + "ic": 510, + "ical": 625, + "ice": 782, + "ich": 561, + "ics": 996, + "id": 463, + "id": 613, + "ide": 739, + "ie": 974, + "ied": 812, + "ies": 516, + "if": 524, + "ig": 444, + "igh": 537, + "ight": 680, + "ik": 775, + "ike": 984, + "il": 406, + "il": 714, + "ile": 721, + "ill": 608, + "ill": 789, + "ily": 950, + "im": 469, + "im": 767, + "ime": 691, + "in": 358, + "in": 501, + "ine": 607, + "ing": 557, + "ing": 383, + "ings": 815, + "ion": 472, + "ion": 408, + "ional": 717, + "ions": 540, + "ip": 733, + "ip": 818, + "ir": 453, + "ir": 554, + "is": 393, + "is": 441, + "ish": 694, + "ish": 654, + "ished": 942, + "ision": 944, + "iss": 876, + "ist": 550, + "ist": 811, + "it": 378, + "it": 746, + "ite": 760, + "ited": 809, + "ition": 797, + "ity": 542, + "iv": 435, + "ive": 549, + "ived": 979, + "iz": 722, + "j": 75, + "j": 288, + "k": 76, + "k": 210, + "ked": 810, + "king": 924, + "ks": 692, + "l": 77, + "l": 201, + "la": 467, + "land": 743, + "ld": 559, + "le": 536, + "le": 465, + "les": 799, + "lud": 718, + "ly": 433, + "m": 78, + "m": 202, + "ment": 701, + "mp": 651, + "n": 79, + "n": 199, + "nd": 369, + "ned": 758, + "ning": 843, + "o": 80, + "o": 198, + "ob": 920, + "oc": 534, + "od": 575, + "og": 604, + "oh": 972, + "oin": 831, + "ol": 428, + "oll": 703, + "ollow": 928, + "olog": 932, + "om": 419, + "om": 883, + "ome": 663, + "on": 382, + "on": 390, + "ond": 872, + "one": 835, + "ong": 850, + "ong": 582, + "oo": 517, + "ood": 927, + "ook": 897, + "op": 531, + "op": 971, + "or": 377, + "or": 424, + "ore": 571, + "ors": 917, + "ort": 768, + "ort": 752, + "ory": 737, + "os": 447, + "ose": 881, + "ost": 646, + "ot": 600, + "ot": 879, + "ou": 392, + "oug": 659, + "ough": 798, + "ould": 640, + "oun": 553, + "ound": 961, + "our": 648, + "our": 772, + "ous": 712, + "out": 683, + "outh": 945, + "ov": 515, + "ow": 461, + "ow": 666, + "own": 657, + "oy": 952, + "p": 81, + "p": 217, + "per": 715, + "ph": 916, + "pp": 518, + "q": 82, + "q": 280, + "qu": 546, + "r": 83, + "r": 204, + "ra": 457, + "ran": 624, + "re": 367, + "ree": 765, + "ren": 790, + "res": 572, + "res": 747, + "ri": 487, + "rib": 804, + "ric": 745, + "rit": 589, + "ro": 385, + "rom": 498, + "rop": 826, + "roug": 803, + "ru": 951, + "ruc": 891, + "ry": 908, + "s": 84, + "s": 206, + "se": 741, + "sh": 795, + "so": 630, + "sp": 992, + "ss": 673, + "st": 519, + "st": 528, + "t": 85, + "t": 208, + "te": 954, + "ted": 489, + "ter": 535, + "ter": 505, + "th": 449, + "th": 488, + "ther": 576, + "ting": 676, + "tion": 570, + "tr": 619, + "ts": 436, + "tt": 720, + "tur": 953, + "ty": 821, + "u": 86, + "u": 229, + "ub": 591, + "ubl": 842, + "uc": 490, + "ud": 538, + "ue": 652, + "ug": 560, + "uil": 930, + "ul": 494, + "um": 532, + "um": 644, + "un": 448, + "und": 828, + "up": 833, + "up": 700, + "ur": 413, + "ure": 635, + "uring": 702, + "ury": 957, + "us": 438, + "us": 622, + "ust": 846, + "ut": 529, + "ut": 527, + "v": 87, + "v": 232, + "ve": 567, + "vi": 866, + "w": 88, + "w": 250, + "way": 970, + "wn": 999, + "x": 89, + "x": 269, + "y": 90, + "y": 211, + "yp": 993, + "z": 91, + "z": 228, + "|": 92, + "|": 304, + "}": 93, + "}": 336, + "~": 94, + "~": 343, + "¡": 95, + "¡": 220, + "¢": 96, + "¢": 306, + "£": 97, + "£": 323, + "¤": 98, + "¤": 292, + "¥": 99, + "¥": 339, + "¦": 100, + "¦": 303, + "§": 101, + "§": 275, + "¨": 102, + "¨": 282, + "©": 103, + "©": 259, + "ª": 104, + "ª": 286, + "«": 105, + "«": 266, + "¬": 106, + "¬": 319, + "®": 107, + "®": 329, + "¯": 108, + "¯": 287, + "°": 109, + "°": 298, + "±": 110, + "±": 200, + "²": 111, + "²": 284, + "³": 112, + "³": 272, + "´": 113, + "´": 307, + "µ": 114, + "µ": 261, + "¶": 115, + "¶": 301, + "·": 116, + "·": 326, + "¸": 117, + "¸": 257, + "¹": 118, + "¹": 241, + "º": 119, + "º": 260, + "»": 120, + "»": 247, + "¼": 121, + "¼": 305, + "½": 122, + "½": 294, + "¾": 123, + "¾": 316, + "¿": 124, + "¿": 271, + "Â": 125, + "Ã": 126, + "Ä": 127, + "Å": 128, + "Æ": 129, + "Ç": 130, + "È": 131, + "É": 132, + "Ê": 133, + "Ë": 134, + "Ì": 135, + "Í": 136, + "Î": 137, + "Ï": 138, + "Ð": 139, + "Ñ": 140, + "Ö": 141, + "×": 142, + "Ø": 143, + "Ù": 144, + "Ü": 145, + "à": 146, + "á": 147, + "â": 148, + "ã": 149, + "ä": 150, + "å": 151, + "æ": 152, + "ç": 153, + "è": 154, + "é": 155, + "ë": 156, + "ì": 157, + "ï": 158, + "Ċ": 159, + "Ċ": 349, + "Ġ": 160, + "Ġ\"": 401, + "Ġ'": 431, + "Ġ(": 475, + "Ġ)": 474, + "Ġ,": 360, + "Ġ.": 365, + "Ġ0": 847, + "Ġ1": 411, + "Ġ18": 769, + "Ġ19": 492, + "Ġ199": 893, + "Ġ1": 778, + "Ġ2": 462, + "Ġ20": 522, + "Ġ200": 620, + "Ġ201": 734, + "Ġ2": 813, + "Ġ3": 735, + "Ġ3": 888, + "Ġ4": 870, + "Ġ5": 907, + "Ġ5": 990, + "Ġ:": 637, + "Ġ;": 615, + "Ġ": 333, + "Ġ=": 399, + "Ġ@": 417, + "Ġ@,@": 755, + "Ġ@-@": 440, + "Ġ@.@": 696, + "ĠA": 409, + "ĠA": 807, + "ĠAl": 716, + "ĠAm": 829, + "ĠAmeric": 958, + "ĠAn": 784, + "ĠAr": 894, + "ĠB": 432, + "ĠC": 410, + "ĠCh": 581, + "ĠCom": 904, + "ĠD": 464, + "ĠE": 500, + "ĠEn": 878, + "ĠF": 470, + "ĠG": 482, + "ĠH": 445, + "ĠHe": 742, + "ĠI": 442, + "ĠI": 827, + "ĠIn": 704, + "ĠIn": 574, + "ĠIt": 774, + "ĠJ": 491, + "ĠK": 548, + "ĠL": 484, + "ĠM": 423, + "ĠMar": 776, + "ĠN": 483, + "ĠO": 504, + "ĠP": 450, + "ĠPar": 967, + "ĠR": 459, + "ĠS": 403, + "ĠSh": 750, + "ĠSt": 590, + "ĠT": 396, + "ĠTh": 414, + "ĠThe": 437, + "ĠThis": 997, + "ĠU": 585, + "ĠUn": 773, + "ĠV": 617, + "ĠW": 479, + "ĠWh": 853, + "ĠY": 757, + "Ġa": 356, + "Ġa": 394, + "Ġab": 653, + "Ġabout": 899, + "Ġac": 583, + "Ġacc": 874, + "Ġad": 656, + "Ġafter": 763, + "Ġag": 725, + "Ġal": 476, + "Ġalb": 991, + "Ġall": 839, + "Ġalso": 641, + "Ġan": 602, + "Ġan": 562, + "Ġand": 381, + "Ġapp": 711, + "Ġar": 507, + "Ġare": 601, + "Ġas": 454, + "Ġass": 947, + "Ġat": 514, + "Ġatt": 788, + "Ġb": 371, + "Ġbe": 499, + "Ġbe": 595, + "Ġbec": 706, + "Ġbeen": 686, + "Ġbeg": 915, + "Ġbetween": 914, + "Ġbo": 819, + "Ġbut": 623, + "Ġby": 473, + "Ġc": 368, + "Ġcent": 823, + "Ġch": 526, + "Ġchar": 822, + "Ġcl": 689, + "Ġcom": 509, + "Ġcomm": 707, + "Ġcomp": 616, + "Ġcon": 477, + "Ġcons": 841, + "Ġcont": 655, + "Ġcre": 931, + "Ġd": 387, + "Ġde": 627, + "Ġdec": 873, + "Ġdef": 965, + "Ġdes": 738, + "Ġdi": 892, + "Ġdis": 708, + "Ġduring": 864, + "Ġe": 421, + "Ġear": 854, + "Ġel": 869, + "Ġen": 662, + "Ġev": 682, + "Ġex": 539, + "Ġexp": 867, + "Ġf": 370, + "Ġfe": 845, + "Ġfil": 913, + "Ġfin": 786, + "Ġfir": 599, + "Ġfirst": 626, + "Ġfl": 877, + "Ġfor": 614, + "Ġfor": 458, + "Ġform": 963, + "Ġfrom": 503, + "Ġg": 430, + "Ġgame": 895, + "Ġgen": 985, + "Ġgro": 890, + "Ġh": 380, + "Ġha": 485, + "Ġhad": 566, + "Ġhas": 679, + "Ġhave": 667, + "Ġhe": 558, + "Ġher": 660, + "Ġhim": 896, + "Ġhis": 512, + "Ġi": 366, + "Ġimp": 909, + "Ġin": 429, + "Ġin": 389, + "Ġinc": 618, + "Ġinclud": 761, + "Ġind": 983, + "Ġint": 628, + "Ġinter": 832, + "Ġinto": 785, + "Ġis": 480, + "Ġit": 533, + "Ġits": 642, + "Ġj": 723, + "Ġk": 564, + "Ġkn": 857, + "Ġl": 398, + "Ġlar": 962, + "Ġlater": 936, + "Ġlea": 868, + "Ġm": 386, + "Ġmade": 949, + "Ġme": 968, + "Ġmore": 802, + "Ġmost": 910, + "Ġmov": 956, + "Ġmus": 966, + "Ġn": 415, + "Ġnew": 989, + "Ġno": 547, + "Ġnor": 978, + "Ġnot": 632, + "Ġnum": 926, + "Ġo": 359, + "Ġof": 373, + "Ġoff": 875, + "Ġon": 551, + "Ġon": 456, + "Ġone": 677, + "Ġonly": 871, + "Ġor": 699, + "Ġor": 645, + "Ġother": 787, + "Ġout": 925, + "Ġov": 729, + "Ġover": 856, + "Ġp": 379, + "Ġpar": 636, + "Ġper": 736, + "Ġpl": 698, + "Ġpla": 697, + "Ġplay": 808, + "Ġpos": 859, + "Ġpr": 889, + "Ġpre": 749, + "Ġpres": 912, + "Ġpro": 506, + "Ġproduc": 934, + "Ġqu": 955, + "Ġr": 521, + "Ġra": 863, + "Ġre": 400, + "Ġrec": 597, + "Ġrecor": 919, + "Ġreg": 943, + "Ġrel": 900, + "Ġrele": 946, + "Ġrem": 848, + "Ġrep": 762, + "Ġres": 650, + "Ġro": 629, + "Ġs": 361, + "Ġsa": 905, + "Ġsc": 732, + "Ġse": 569, + "Ġseason": 948, + "Ġsec": 781, + "Ġser": 740, + "Ġsev": 884, + "Ġsh": 513, + "Ġshe": 862, + "Ġsp": 578, + "Ġspec": 940, + "Ġst": 446, + "Ġstar": 939, + "Ġsu": 770, + "Ġsub": 969, + "Ġsuc": 764, + "Ġsuch": 981, + "Ġt": 354, + "Ġth": 355, + "Ġthan": 918, + "Ġthat": 452, + "Ġthe": 502, + "Ġthe": 357, + "Ġtheir": 621, + "Ġthem": 998, + "Ġthey": 727, + "Ġthis": 705, + "Ġthree": 902, + "Ġthroug": 923, + "Ġtime": 783, + "Ġto": 391, + "Ġtra": 836, + "Ġtw": 639, + "Ġtwo": 688, + "Ġun": 544, + "Ġup": 898, + "Ġus": 668, + "Ġused": 988, + "Ġv": 495, + "Ġw": 363, + "Ġwas": 422, + "Ġwere": 525, + "Ġwh": 443, + "Ġwhen": 851, + "Ġwhere": 995, + "Ġwhich": 573, + "Ġwhile": 935, + "Ġwho": 724, + "Ġwit": 451, + "Ġwith": 994, + "Ġwith": 466, + "Ġwor": 643, + "Ġwould": 801, + "Ġwrit": 937, + "Ġy": 580, + "Ġyear": 987, + "Ġâ": 556, + "ĠâĢ": 565, + "ĠâĢĵ": 631, + "ĠĊ": 412, + "Ģ": 161, + "Ģ": 223, + "ģ": 162, + "ģ": 273, + "Ĥ": 163, + "Ĥ": 262, + "ĥ": 164, + "ĥ": 337, + "Ħ": 165, + "Ħ": 278, + "ħ": 166, + "ħ": 281, + "Ĩ": 167, + "Ĩ": 308, + "ĩ": 168, + "ĩ": 225, + "Ī": 169, + "Ī": 221, + "ī": 170, + "ī": 244, + "Ĭ": 171, + "Ĭ": 315, + "ĭ": 172, + "ĭ": 321, + "Į": 173, + "Į": 324, + "į": 174, + "į": 302, + "İ": 175, + "İ": 249, + "ı": 176, + "ı": 332, + "IJ": 177, + "IJ": 295, + "ij": 178, + "ij": 313, + "Ĵ": 179, + "Ĵ": 328, + "ĵ": 180, + "ĵ": 312, + "Ķ": 181, + "Ķ": 256, + "ķ": 182, + "ķ": 314, + "ĸ": 183, + "ĸ": 277, + "Ĺ": 184, + "Ĺ": 322, + "ĺ": 185, + "ĺ": 285, + "Ļ": 186, + "Ļ": 267, + "ļ": 187, + "ļ": 290, + "Ľ": 188, + "Ľ": 311, + "ľ": 189, + "ľ": 299, + "Ŀ": 190, + "Ŀ": 291, + "ŀ": 191, + "ŀ": 293, + "Ł": 192, + "Ł": 335, + "ł": 193, + "ł": 252, + "Ń": 194, + "Ń": 297 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/unet/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f9ec9480b77f5dd277f970bffda5aec4873b85ca --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/unet/config.json @@ -0,0 +1,97 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "reverse_transformer_layers_per_block", + "attention_type", + "dropout" + ], + "act_fn": "silu", + "addition_embed_type": "text_time", + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": 8, + "attention_head_dim": [ + 2, + 4 + ], + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 64, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "unet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": 80, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "sample_size": 32, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": [ + 1, + 2 + ], + "transformers_version": null, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": true +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/unet/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/unet/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..cff7996ad969f0a0923d8cf00d65583c6273cd32 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/unet/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a315f60fd66c608c0f0503b2e88045108df156245ded0e75a3d0d28df985c021 +size 3960703 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_decoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_decoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..6e75faef23c857c5e37c93844ab4285a0774b1fa --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_decoder/config.json @@ -0,0 +1,63 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "latents_std", + "force_upcast", + "use_quant_conv", + "use_post_quant_conv", + "latents_mean", + "mid_block_add_attention", + "shift_factor" + ], + "act_fn": "silu", + "block_out_channels": [ + 32, + 64 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 1, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "vae-decoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 32, + "out_channels": 3, + "output_attentions": false, + "sample_size": 128, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_decoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_decoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..906827aed04451a97236a6bd27f64279aeece12b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_decoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cffce317c46c43a2b749ceaaa6fcf9fa585548db7fd2aa15e8c31109b34941d +size 1905139 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_encoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..fe46e32e7cd5beedb1d0cc227b42165c8c64247e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_encoder/config.json @@ -0,0 +1,63 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "latents_std", + "force_upcast", + "use_quant_conv", + "use_post_quant_conv", + "latents_mean", + "mid_block_add_attention", + "shift_factor" + ], + "act_fn": "silu", + "block_out_channels": [ + 32, + 64 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 1, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "vae-encoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 64, + "static_num_channels": 3, + "static_width": 64, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 32, + "out_channels": 3, + "output_attentions": false, + "sample_size": 128, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_encoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..480e467b28b100cda24168a29c3c23ae2b3e3c00 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5df183a9a537186b793f/vae_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5a259fe22328b076e3b4241bc466777a3cc58c18f5ecd4c27de0efbf23c3cc +size 1441459 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..271ba141edfacd26be5dcbf08c27c80f6a43774b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00a1c3141aad792861776edfe195b433cbbe508c1c302bde2db3042f3c24b81b +size 2428099 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..639556ebcff563eb83ee1eafb1af46c982516074 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2c16a9ab168d3c3b441049afdddaf29a354ebb986b7764841d95396de158bd4 +size 2653184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..34b34842ca22bcc5263ce39cae89d407766badde --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_5e0601a3382db348dc1e+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79a6aaa578480c5af7e0ebb0701be3330c4ca567dabba1a8eb3d34256ec8da64 +size 2813329 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..10880a1a48a6d3e324e2d2b947237965bfe7029a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6eadac5b46718f86a1caf26c09bbfa58f3791fcf575865ac88d104cb0b566ba4 +size 1003294 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b72c229a5266bc5d6fe92c3b23f0168e4a356f39 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_601ad14244daafd4e761+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6bea7eaf64552d3fea1f24e3b2c1ef85d13b90ce49c8b00e9a084bca384c5a4 +size 5633024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..680cf1673eb938f5fc992c230a7db7517770a04b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9347f729c457666f205465d41556977d4ccefa5e621734bee8881a0a03d1999b +size 1843628 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..44f33fe4866ae56706f5bc39400e5de3d8162953 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a127c57c06792c678c22bc779de2108567364dd59e8326ad8ad6ea96bbf54e +size 1158144 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..da4a81af2164f01bc9d70d7d148e3abbfe8aa56e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_617f751c1ee43436fa2c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23e668e7978d03815799c043e5d19fcddda3c2c72c834679ece17c523dccce8a +size 1280533 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..98185f920a6e73e856358de8491bb6b3fcf3c34f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0584f64a0483db223fb6580ef12695c923875603c29aaa9f1e13171d7c9d7305 +size 1853014 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f66ddbae75438aed044417f02f84d3e44e10c3ef --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_61b53359a0a31e597238+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989f2efa327fe2ba8c8f29b10c063b3fb039649a6ebd63981d250c7b28c9e057 +size 10783744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8708f500fa9dbe3756e648878839741ef1621ff5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..71ad4bddb1f9494960b2528be7829f553c7c1155 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc12474d27a351ca8ee9ba0df70c21763f2cf564a097c0348db88ffaf69bae21 +size 1712818 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..14912171565ef3ae7470c1d527d2f7f21e26ebbd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_63365ed7d18a04195fe5+97496b47/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:943311e0016cfdcfa3025f69c9013f4204c0d92c96684c6fb39767a4ef8b424d +size 39721984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0d3b7edefd9abba73b2f34d3e573a37b58d09693 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a2d3d03b693c2c78178a5b217c1d5a614c789a8658a787afbc1e20b12fe8c1b +size 4849492 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..92a295819f4777bd4997cc6d03f971df9a14a6a5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_672d3fac8fde8fb30afb+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c8bf77f35cc1af04e1b4a8d193b99bb07ca07c636f3fb2aece66e9e78d92381 +size 10947584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dbc1e20c6e979343e16bdb54705634b17d501955 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cbb70674d43a79e877fa0e937f7247ee31b03e864e8797460dc911ef21153d5 +size 204291 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..efa382a79d24d2c85afaf583f944c88737eedaac --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_693e831be92621c50b6f+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c01053853e045806e2855ef7791f3d955bd07797bdc4e94fb6274d3a166fec5 +size 287744 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b2e06eb7526456ddce055020332cdaa305fc93ef --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab99eaef4f8cfe67b8635506cae450003067f2d7358b0685d9075c56b200df60 +size 2804218 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6bb8c23fb998abaaa00070362b0308ce265c9abb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6ac0045a775dbb747ff4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59a0e88589747a3d70246ba78b251b727f56b60e830df7fc927addd5e8cb5b00 +size 7650304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6c9f73c911132eacee1474512b70a95cb7103df --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bd44916777f28aa5d0f202b790ed2f57ec9d546c3cb6c3a7037c9257f171797 +size 3057017 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5667a80b5ec50c28d05b78299982586bc5990d19 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3ad7ebe4a3547a6aa72bfb6bf85ad4efe1f07a8e9c235bffc298f58b6d004f1 +size 5315584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..abb52eae9d7616a2cb45f6e2a9b9b73bd9780125 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6b694cb6a93ff1492ff7+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5145b828a4538670df3057bbbde77ab136cd24d298d39bc093c9d9f93084ef4 +size 5482108 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6e40368c46e9a7e4622db09cd45f5152f4500779 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49c91fe39fb815d01e3bbc6c1c81466e81be8390a7051c031320c77ff384ba87 +size 3257789 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f7d681db884a041a40a17cdd1d106b479b2c616d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6df920de2413af901e26+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5b5ec23c0f4ca4c8aa8501fe370ce8d03828789bd021e226f5a570e4e87be51 +size 19303424 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6798521854e47472fe9591cf34c6729c2097cdf8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4b2a755db1c0509d1d970e377c09cab63c65d91274067368f2e2fdabea8b649 +size 2274046 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5d8ed9336c9c01e9afeeab5eb041bb01f5494187 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618f38d56dba9d26ae2a617050fc5e1978d3bb342403cad5a1dbd1424778cb84 +size 3277824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4a134f06478c8e6ef4a0c897d4b3e0967236c633 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6e73b50052e4c5001580+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20703fe3b56d84e7e64373c4c0c22f3923a88390e979875c621537ca1861e9d3 +size 3415603 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6577cb2341793ee551ff3ca3c86ae2f5e805c73f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e0e1e879c076b664f278a770717aaf717d64f9b7e2f9afdf6dff7d1e6d56de +size 1842898 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8eca6a6362b47ca997d0df92386c7a34bb6da76f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3c5f1a23fcca4f5c6802eb605a9696205e2ca536ded7d1ab57b8e2b3a23704c +size 1342464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8f3594bb4f538fe56a14a55eec4bd761cfa9e915 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_6f5fa2b092920992ce0b+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3837e7ba2ca5a9a4c715b977c28039cd2a7c228de93818ce458ef6cfe41b1efb +size 1464853 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bdc32e9812f434e9fc9dfa2e784b74801cdf1758 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87f572a0a29187ca3f20129938adc28be8ff34ddcaaac0d0ee9a53ca0c7343f1 +size 2030520 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6b28b86c95fefaf67f49421685824f0251ab7325 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_706a16b21bfca50c4ce2+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0a86bae90e6c404c6dc807e1b0836fba7554f9a9c6ae28534aaadeb65ec0663 +size 3410944 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..23333f396509c6f3747252892313dc013437409a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/compile_flags.json @@ -0,0 +1 @@ +["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..538d24eb4bd67a8ba760add803dd9d464de06707 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b224244b6ba07f7aec2feffbdc1e1ce476bcb327e579e676e39321787b0f69a +size 258494 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9d880b92420c7a7fd9eb0c4f0f75c4567cbb0ccf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_738b2e2b8defa3f16694+e457fe88/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e6e047b663fac0ba12512caed6d51e32de3b3c9aeb1f0200abd6f0e33ad227 +size 318601 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/feature_extractor/preprocessor_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/feature_extractor/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fb1692ff11ed6b3dee0634f577193bb23c0d37ec --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/feature_extractor/preprocessor_config.json @@ -0,0 +1,27 @@ +{ + "crop_size": { + "height": 224, + "width": 224 + }, + "do_center_crop": true, + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "CLIPImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "shortest_edge": 224 + } +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/model_index.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/model_index.json new file mode 100644 index 0000000000000000000000000000000000000000..87739957b2e5a5cbfc097a380e4c1fd821edff1e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/model_index.json @@ -0,0 +1,38 @@ +{ + "_class_name": "StableDiffusionPipeline", + "_diffusers_version": "0.35.2", + "_name_or_path": "hf-internal-testing/tiny-stable-diffusion-torch", + "feature_extractor": [ + "transformers", + "CLIPImageProcessor" + ], + "image_encoder": [ + null, + null + ], + "requires_safety_checker": true, + "safety_checker": [ + null, + null + ], + "scheduler": [ + "diffusers", + "PNDMScheduler" + ], + "text_encoder": [ + "transformers", + "CLIPTextModel" + ], + "tokenizer": [ + "transformers", + "CLIPTokenizer" + ], + "unet": [ + "diffusers", + "UNet2DConditionModel" + ], + "vae": [ + "diffusers", + "AutoencoderKL" + ] +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/scheduler/scheduler_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..ebd5ba3f2aa29ce01f09e33abb7073aa9c1c6827 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/scheduler/scheduler_config.json @@ -0,0 +1,15 @@ +{ + "_class_name": "PNDMScheduler", + "_diffusers_version": "0.35.2", + "beta_end": 0.012, + "beta_schedule": "scaled_linear", + "beta_start": 0.00085, + "clip_sample": false, + "num_train_timesteps": 1000, + "prediction_type": "epsilon", + "set_alpha_to_one": false, + "skip_prk_steps": true, + "steps_offset": 1, + "timestep_spacing": "leading", + "trained_betas": null +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/text_encoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..b48da21d78c3f77b5e3875b825a415019e391468 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/text_encoder/config.json @@ -0,0 +1,46 @@ +{ + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dropout": 0.0, + "dtype": "float32", + "eos_token_id": 2, + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 37, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "clip-text-model", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 4, + "num_hidden_layers": 5, + "pad_token_id": 1, + "projection_dim": 512, + "return_dict": false, + "torchscript": true, + "transformers_version": "4.57.6", + "vocab_size": 1000 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/text_encoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/text_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..e8966e4e80b0571f89555b1e7028678ebd92b27c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/text_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c73a632b5072b464e3887f02053fc37ee5dcab772e2e1bf1c4e29897f3dbf4ec +size 811763 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/merges.txt b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/merges.txt new file mode 100644 index 0000000000000000000000000000000000000000..e9193d6fc11f7b6e281b4686221363b6cdc4e576 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/merges.txt @@ -0,0 +1,647 @@ +#version: 0.2 +Ġ t +Ġt h +Ġ a +Ġth e +i n +Ġ o +Ġ , +Ġ s +e d +Ġ w +e r +Ġ . +Ġ i +r e +Ġ c +n d +Ġ f +Ġ b +a t +Ġo f +e r +e n +a r +o r +i t +Ġ p +Ġ h +Ġa nd +o n +in g +a n +r o +Ġ m +Ġ d +e s +Ġi n +o n +Ġt o +o u +i s +Ġ a +i c +Ġ T +a l +Ġ l +Ġ = +Ġ re +Ġ " +e s +Ġ S +a s +a l +i l +e l +i on +Ġ A +Ġ C +Ġ 1 +Ġ Ċ +u r +ĠT h +Ġ n +a s +Ġ @ +e c +o m +a c +Ġ e +Ġw as +Ġ M +o r +a n +a m +e n +o l +Ġ in +Ġ g +Ġ ' +Ġ B +l y +a t +i v +t s +ĠTh e +u s +- @ +Ġ@ -@ +i s +Ġ I +Ġw h +i g +Ġ H +Ġs t +o s +u n +t h +Ġ P +Ġw it +Ġth at +i r +Ġa s +e m +Ġo n +r a +Ġf or +Ġ R +e t +o w +Ġ 2 +i d +Ġ D +l e +Ġwit h +l a +en t +i m +Ġ F +e a +i on +Ġb y +Ġ ) +Ġ ( +Ġa l +Ġc on +en t +Ġ W +Ġi s +er e +Ġ G +Ġ N +Ġ L +Ġh a +er s +r i +t h +t ed +u c +Ġ J +Ġ1 9 +e v +u l +Ġ v +c e +at ion +ro m +Ġb e +Ġ E +i n +Ġth e +Ġf rom +Ġ O +t er +Ġp ro +Ġa r +a d +Ġc om +i c +a g +Ġh is +Ġs h +Ġa t +o v +i es +o o +p p +s t +c h +Ġ r +Ġ2 0 +a y +i f +Ġw ere +Ġc h +u t +s t +u t +d s +o p +u m +Ġi t +o c +t er +l e +ig h +u d +Ġe x +ion s +at e +it y +at ed +Ġ un +e p +q u +Ġn o +Ġ K +iv e +is t +Ġo n +am e +ou n +i r +a b +Ġ â +in g +Ġh e +l d +u g +ic h +Ġa n +e d +Ġ k +Ġâ Ģ +Ġha d +v e +a in +Ġs e +t ion +or e +re s +Ġwh ich +ĠI n +o d +th er +a k +Ġs p +a r +Ġ y +ĠC h +on g +Ġa c +es t +Ġ U +a p +f f +al ly +r it +ĠS t +u b +g e +b er +e t +Ġb e +e ar +Ġre c +er s +Ġf ir +o t +Ġar e +Ġa n +c h +o g +i a +es t +in e +il l +an d +e l +ar y +e w +i d +Ġf or +Ġ ; +Ġcom p +Ġ V +Ġin c +t r +Ġ20 0 +Ġthe ir +u s +Ġb ut +r an +ic al +Ġfir st +Ġd e +Ġin t +Ġ ro +s o +ĠâĢ ĵ +Ġno t +d ing +f ter +ur e +Ġp ar +Ġ : +i an +Ġt w +ou ld +Ġal so +Ġi ts +Ġw or +u m +Ġo r +os t +0 0 +ou r +ar d +Ġre s +m p +u e +Ġa b +is h +Ġcon t +Ġa d +ow n +al l +ou g +Ġh er +as t +Ġ en +om e +al l +d ed +o w +Ġha ve +Ġ us +ea r +ac k +d uc +i al +s s +en ts +a in +t ing +Ġon e +es s +Ġh as +igh t +a v +Ġe v +ou t +a y +en ce +Ġbe en +e w +Ġtw o +Ġc l +d er +im e +k s +es s +is h +. @ +Ġ@ .@ +Ġp la +Ġp l +Ġo r +u p +m ent +ur ing +ol l +ĠI n +Ġth is +Ġb ec +Ġcom m +Ġd is +at er +ag e +Ġa pp +ou s +e y +i l +p er +ĠA l +ion al +l ud +el y +t t +il e +i z +Ġ j +Ġwh o +Ġa g +i b +Ġthe y +f or +Ġo v +at h +e g +Ġs c +i p +Ġ20 1 +Ġ 3 +Ġp er +or y +Ġd es +id e +Ġs er +s e +ĠH e +la nd +at ions +r ic +i t +re s +er ed +Ġp re +ĠS h +an ce +or t +an t +, @ +Ġ@ ,@ +el l +Ġ Y +n ed +el l +it e +Ġinc lud +Ġre p +Ġa fter +Ġs uc +re e +an y +i m +or t +Ġ1 8 +Ġs u +ad e +ou r +ĠU n +ĠI t +i k +ĠM ar +em ber +Ġ 1 +e en +a nd +Ġs ec +ic e +Ġt ime +ĠA n +Ġint o +Ġf in +Ġo ther +Ġa tt +il l +re n +ac h +as s +er al +es e +s h +al s +it ion +oug h +l es +am p +Ġw ould +Ġm ore +ro ug +ri b +er y +ac e +Ġ A +Ġpla y +it ed +k ed +is t +i ed +Ġ 2 +as ed +ing s +an g +a m +i p +Ġb o +ab le +t y +Ġch ar +Ġc ent +et w +at es +ro p +Ġ I +u nd +ĠA m +c es +o in +Ġin ter +u p +c t +on e +Ġt ra +an t +ec t +Ġal l +e f +Ġcon s +ub l +n ing +an s +Ġf e +us t +Ġ 0 +Ġre m +as e +on g +Ġwh en +e b +ĠW h +Ġe ar +ev er +Ġov er +Ġk n +a us +Ġp os +a d +er m +Ġsh e +Ġ ra +Ġd uring +as on +v i +Ġex p +Ġl ea +Ġ el +Ġ 4 +Ġon ly +o nd +Ġd ec +Ġac c +Ġo ff +is s +Ġf l +ĠE n +o t +en s +os e +ak e +o m +Ġs ev +ac h +etw een +er n +Ġ 3 +Ġp r +Ġg ro +r uc +Ġd i +Ġ19 9 +ĠA r +Ġg ame +Ġh im +oo k +Ġ up +Ġab out +Ġre l +for m +Ġth ree +at t +ĠC om +Ġs a +ear s +Ġ 5 +r y +Ġi mp +Ġm ost +f er +Ġp res +Ġf il +Ġb etween +Ġbe g +p h +or s +Ġth an +Ġrec or +o b +er ic +at ing +Ġth roug +k ing +Ġo ut +Ġn um +oo d +oll ow +ac t +u il +Ġc re +ol og +at ional +Ġpro duc +Ġwh ile +Ġl ater +Ġw rit +e x +Ġst ar +Ġsp ec +e e +ish ed +Ġre g +is ion +ou th +Ġre le +Ġa ss +Ġse ason +Ġm ade +il y +r u +o y +t ur +t e +Ġ qu +Ġm ov +ur y +ĠAm eric +em ent +c c +ou nd +Ġl ar +Ġfor m +ec t +Ġde f +Ġm us +ĠP ar +Ġm e +Ġs ub +w ay +o p +o h +el d +i e +em p +am es +er n +Ġn or +iv ed +ev el +Ġsuc h +ar ds +Ġin d +ik e +Ġg en +er t +Ġy ear +Ġus ed +Ġn ew +Ġ 5 +Ġal b +s p +y p +Ġwit h +Ġwh ere +ic s +ĠTh is +Ġthe m +w n diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/special_tokens_map.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..2c2130b544c0c5a72d5d00da071ba130a9800fb2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/special_tokens_map.json @@ -0,0 +1,24 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "pad_token": "<|endoftext|>", + "unk_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + } +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/tokenizer_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3f6c8728339a38e4ba04cb91e3d80bb46d384280 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/tokenizer_config.json @@ -0,0 +1,31 @@ +{ + "add_prefix_space": false, + "added_tokens_decoder": { + "0": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": false, + "do_lower_case": true, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 77, + "pad_token": "<|endoftext|>", + "tokenizer_class": "CLIPTokenizer", + "unk_token": "<|endoftext|>" +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/vocab.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/vocab.json new file mode 100644 index 0000000000000000000000000000000000000000..609c08ebb708079189a79c6964c3495e36b26f41 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/tokenizer/vocab.json @@ -0,0 +1,1002 @@ +{ + "!": 2, + "!": 345, + "\"": 3, + "\"": 344, + "#": 4, + "#": 325, + "$": 5, + "$": 348, + "%": 6, + "%": 351, + "&": 7, + "&": 352, + "'": 8, + "'": 296, + "(": 9, + "(": 318, + ")": 10, + ")": 330, + "*": 11, + "*": 327, + "+": 12, + "+": 341, + ",": 13, + ",": 279, + ",@": 754, + "-": 14, + "-": 276, + "-@": 439, + ".": 15, + ".": 253, + ".@": 695, + "/": 16, + "/": 350, + "0": 17, + "00": 647, + "0": 216, + "1": 18, + "1": 222, + "2": 19, + "2": 231, + "3": 20, + "3": 243, + "4": 21, + "4": 233, + "5": 22, + "5": 240, + "6": 23, + "6": 226, + "7": 24, + "7": 215, + "8": 25, + "8": 236, + "9": 26, + "9": 242, + ":": 27, + ":": 353, + ";": 28, + ";": 317, + "<": 29, + "<": 340, + "<|endoftext|>": 1, + "<|startoftext|>": 0, + "=": 30, + "=": 342, + ">": 31, + ">": 300, + "?": 32, + "?": 346, + "@": 33, + "@": 320, + "A": 34, + "A": 227, + "B": 35, + "B": 258, + "C": 36, + "C": 239, + "D": 37, + "D": 255, + "E": 38, + "E": 246, + "F": 39, + "F": 213, + "G": 40, + "G": 283, + "H": 41, + "H": 219, + "I": 42, + "I": 237, + "J": 43, + "J": 251, + "K": 44, + "K": 254, + "L": 45, + "L": 218, + "M": 46, + "M": 234, + "N": 47, + "N": 238, + "O": 48, + "O": 265, + "P": 49, + "P": 245, + "Q": 50, + "Q": 309, + "R": 51, + "R": 264, + "S": 52, + "S": 230, + "T": 53, + "T": 235, + "U": 54, + "U": 268, + "V": 55, + "V": 248, + "W": 56, + "W": 274, + "X": 57, + "X": 263, + "Y": 58, + "Y": 310, + "Z": 59, + "Z": 207, + "[": 60, + "[": 270, + "\\": 61, + "\\": 338, + "]": 62, + "]": 289, + "^": 63, + "^": 331, + "_": 64, + "_": 334, + "`": 65, + "`": 347, + "a": 66, + "a": 197, + "ab": 555, + "able": 820, + "ac": 420, + "ace": 806, + "ach": 791, + "ach": 885, + "ack": 670, + "act": 929, + "ad": 508, + "ad": 860, + "ade": 771, + "ag": 511, + "age": 710, + "ain": 568, + "ain": 675, + "ak": 577, + "ake": 882, + "al": 397, + "al": 405, + "all": 664, + "all": 658, + "ally": 588, + "als": 796, + "am": 426, + "am": 817, + "ame": 552, + "ames": 976, + "amp": 800, + "an": 384, + "an": 425, + "ance": 751, + "and": 609, + "and": 780, + "ang": 816, + "ans": 844, + "ant": 837, + "ant": 753, + "any": 766, + "ap": 586, + "ar": 376, + "ar": 579, + "ard": 649, + "ards": 982, + "ary": 611, + "as": 416, + "as": 404, + "ase": 849, + "ased": 814, + "ason": 865, + "ass": 792, + "ast": 661, + "at": 372, + "at": 434, + "ate": 541, + "ated": 543, + "ater": 709, + "ates": 825, + "ath": 730, + "ating": 922, + "ation": 497, + "ational": 933, + "ations": 744, + "att": 903, + "aus": 858, + "av": 681, + "ay": 684, + "ay": 523, + "b": 67, + "b": 212, + "ber": 593, + "c": 68, + "c": 224, + "cc": 960, + "ce": 496, + "ces": 830, + "ch": 520, + "ch": 603, + "ct": 834, + "d": 69, + "d": 196, + "ded": 665, + "der": 690, + "ding": 633, + "ds": 530, + "duc": 671, + "e": 70, + "e": 195, + "ea": 471, + "ear": 596, + "ear": 669, + "ears": 906, + "eb": 852, + "ec": 418, + "ect": 838, + "ect": 964, + "ed": 563, + "ed": 362, + "ee": 941, + "een": 779, + "ef": 840, + "eg": 731, + "el": 407, + "el": 610, + "eld": 973, + "ell": 759, + "ell": 756, + "ely": 719, + "em": 455, + "ember": 777, + "ement": 959, + "emp": 975, + "en": 375, + "en": 427, + "ence": 685, + "ens": 880, + "ent": 478, + "ent": 468, + "ents": 674, + "ep": 545, + "er": 364, + "er": 374, + "eral": 793, + "ere": 481, + "ered": 748, + "eric": 921, + "erm": 861, + "ern": 887, + "ern": 977, + "ers": 598, + "ers": 486, + "ert": 986, + "ery": 805, + "es": 402, + "es": 388, + "ese": 794, + "ess": 678, + "ess": 693, + "est": 606, + "est": 584, + "et": 460, + "et": 594, + "etw": 824, + "etween": 886, + "ev": 493, + "evel": 980, + "ever": 855, + "ew": 687, + "ew": 612, + "ex": 938, + "ey": 713, + "f": 71, + "f": 209, + "fer": 911, + "ff": 587, + "for": 728, + "form": 901, + "fter": 634, + "g": 72, + "g": 214, + "ge": 592, + "h": 73, + "h": 203, + "i": 74, + "i": 205, + "ia": 605, + "ial": 672, + "ian": 638, + "ib": 726, + "ic": 395, + "ic": 510, + "ical": 625, + "ice": 782, + "ich": 561, + "ics": 996, + "id": 463, + "id": 613, + "ide": 739, + "ie": 974, + "ied": 812, + "ies": 516, + "if": 524, + "ig": 444, + "igh": 537, + "ight": 680, + "ik": 775, + "ike": 984, + "il": 406, + "il": 714, + "ile": 721, + "ill": 608, + "ill": 789, + "ily": 950, + "im": 469, + "im": 767, + "ime": 691, + "in": 358, + "in": 501, + "ine": 607, + "ing": 557, + "ing": 383, + "ings": 815, + "ion": 472, + "ion": 408, + "ional": 717, + "ions": 540, + "ip": 733, + "ip": 818, + "ir": 453, + "ir": 554, + "is": 393, + "is": 441, + "ish": 694, + "ish": 654, + "ished": 942, + "ision": 944, + "iss": 876, + "ist": 550, + "ist": 811, + "it": 378, + "it": 746, + "ite": 760, + "ited": 809, + "ition": 797, + "ity": 542, + "iv": 435, + "ive": 549, + "ived": 979, + "iz": 722, + "j": 75, + "j": 288, + "k": 76, + "k": 210, + "ked": 810, + "king": 924, + "ks": 692, + "l": 77, + "l": 201, + "la": 467, + "land": 743, + "ld": 559, + "le": 536, + "le": 465, + "les": 799, + "lud": 718, + "ly": 433, + "m": 78, + "m": 202, + "ment": 701, + "mp": 651, + "n": 79, + "n": 199, + "nd": 369, + "ned": 758, + "ning": 843, + "o": 80, + "o": 198, + "ob": 920, + "oc": 534, + "od": 575, + "og": 604, + "oh": 972, + "oin": 831, + "ol": 428, + "oll": 703, + "ollow": 928, + "olog": 932, + "om": 419, + "om": 883, + "ome": 663, + "on": 382, + "on": 390, + "ond": 872, + "one": 835, + "ong": 850, + "ong": 582, + "oo": 517, + "ood": 927, + "ook": 897, + "op": 531, + "op": 971, + "or": 377, + "or": 424, + "ore": 571, + "ors": 917, + "ort": 768, + "ort": 752, + "ory": 737, + "os": 447, + "ose": 881, + "ost": 646, + "ot": 600, + "ot": 879, + "ou": 392, + "oug": 659, + "ough": 798, + "ould": 640, + "oun": 553, + "ound": 961, + "our": 648, + "our": 772, + "ous": 712, + "out": 683, + "outh": 945, + "ov": 515, + "ow": 461, + "ow": 666, + "own": 657, + "oy": 952, + "p": 81, + "p": 217, + "per": 715, + "ph": 916, + "pp": 518, + "q": 82, + "q": 280, + "qu": 546, + "r": 83, + "r": 204, + "ra": 457, + "ran": 624, + "re": 367, + "ree": 765, + "ren": 790, + "res": 572, + "res": 747, + "ri": 487, + "rib": 804, + "ric": 745, + "rit": 589, + "ro": 385, + "rom": 498, + "rop": 826, + "roug": 803, + "ru": 951, + "ruc": 891, + "ry": 908, + "s": 84, + "s": 206, + "se": 741, + "sh": 795, + "so": 630, + "sp": 992, + "ss": 673, + "st": 519, + "st": 528, + "t": 85, + "t": 208, + "te": 954, + "ted": 489, + "ter": 535, + "ter": 505, + "th": 449, + "th": 488, + "ther": 576, + "ting": 676, + "tion": 570, + "tr": 619, + "ts": 436, + "tt": 720, + "tur": 953, + "ty": 821, + "u": 86, + "u": 229, + "ub": 591, + "ubl": 842, + "uc": 490, + "ud": 538, + "ue": 652, + "ug": 560, + "uil": 930, + "ul": 494, + "um": 532, + "um": 644, + "un": 448, + "und": 828, + "up": 833, + "up": 700, + "ur": 413, + "ure": 635, + "uring": 702, + "ury": 957, + "us": 438, + "us": 622, + "ust": 846, + "ut": 529, + "ut": 527, + "v": 87, + "v": 232, + "ve": 567, + "vi": 866, + "w": 88, + "w": 250, + "way": 970, + "wn": 999, + "x": 89, + "x": 269, + "y": 90, + "y": 211, + "yp": 993, + "z": 91, + "z": 228, + "|": 92, + "|": 304, + "}": 93, + "}": 336, + "~": 94, + "~": 343, + "¡": 95, + "¡": 220, + "¢": 96, + "¢": 306, + "£": 97, + "£": 323, + "¤": 98, + "¤": 292, + "¥": 99, + "¥": 339, + "¦": 100, + "¦": 303, + "§": 101, + "§": 275, + "¨": 102, + "¨": 282, + "©": 103, + "©": 259, + "ª": 104, + "ª": 286, + "«": 105, + "«": 266, + "¬": 106, + "¬": 319, + "®": 107, + "®": 329, + "¯": 108, + "¯": 287, + "°": 109, + "°": 298, + "±": 110, + "±": 200, + "²": 111, + "²": 284, + "³": 112, + "³": 272, + "´": 113, + "´": 307, + "µ": 114, + "µ": 261, + "¶": 115, + "¶": 301, + "·": 116, + "·": 326, + "¸": 117, + "¸": 257, + "¹": 118, + "¹": 241, + "º": 119, + "º": 260, + "»": 120, + "»": 247, + "¼": 121, + "¼": 305, + "½": 122, + "½": 294, + "¾": 123, + "¾": 316, + "¿": 124, + "¿": 271, + "Â": 125, + "Ã": 126, + "Ä": 127, + "Å": 128, + "Æ": 129, + "Ç": 130, + "È": 131, + "É": 132, + "Ê": 133, + "Ë": 134, + "Ì": 135, + "Í": 136, + "Î": 137, + "Ï": 138, + "Ð": 139, + "Ñ": 140, + "Ö": 141, + "×": 142, + "Ø": 143, + "Ù": 144, + "Ü": 145, + "à": 146, + "á": 147, + "â": 148, + "ã": 149, + "ä": 150, + "å": 151, + "æ": 152, + "ç": 153, + "è": 154, + "é": 155, + "ë": 156, + "ì": 157, + "ï": 158, + "Ċ": 159, + "Ċ": 349, + "Ġ": 160, + "Ġ\"": 401, + "Ġ'": 431, + "Ġ(": 475, + "Ġ)": 474, + "Ġ,": 360, + "Ġ.": 365, + "Ġ0": 847, + "Ġ1": 411, + "Ġ18": 769, + "Ġ19": 492, + "Ġ199": 893, + "Ġ1": 778, + "Ġ2": 462, + "Ġ20": 522, + "Ġ200": 620, + "Ġ201": 734, + "Ġ2": 813, + "Ġ3": 735, + "Ġ3": 888, + "Ġ4": 870, + "Ġ5": 907, + "Ġ5": 990, + "Ġ:": 637, + "Ġ;": 615, + "Ġ": 333, + "Ġ=": 399, + "Ġ@": 417, + "Ġ@,@": 755, + "Ġ@-@": 440, + "Ġ@.@": 696, + "ĠA": 409, + "ĠA": 807, + "ĠAl": 716, + "ĠAm": 829, + "ĠAmeric": 958, + "ĠAn": 784, + "ĠAr": 894, + "ĠB": 432, + "ĠC": 410, + "ĠCh": 581, + "ĠCom": 904, + "ĠD": 464, + "ĠE": 500, + "ĠEn": 878, + "ĠF": 470, + "ĠG": 482, + "ĠH": 445, + "ĠHe": 742, + "ĠI": 442, + "ĠI": 827, + "ĠIn": 704, + "ĠIn": 574, + "ĠIt": 774, + "ĠJ": 491, + "ĠK": 548, + "ĠL": 484, + "ĠM": 423, + "ĠMar": 776, + "ĠN": 483, + "ĠO": 504, + "ĠP": 450, + "ĠPar": 967, + "ĠR": 459, + "ĠS": 403, + "ĠSh": 750, + "ĠSt": 590, + "ĠT": 396, + "ĠTh": 414, + "ĠThe": 437, + "ĠThis": 997, + "ĠU": 585, + "ĠUn": 773, + "ĠV": 617, + "ĠW": 479, + "ĠWh": 853, + "ĠY": 757, + "Ġa": 356, + "Ġa": 394, + "Ġab": 653, + "Ġabout": 899, + "Ġac": 583, + "Ġacc": 874, + "Ġad": 656, + "Ġafter": 763, + "Ġag": 725, + "Ġal": 476, + "Ġalb": 991, + "Ġall": 839, + "Ġalso": 641, + "Ġan": 602, + "Ġan": 562, + "Ġand": 381, + "Ġapp": 711, + "Ġar": 507, + "Ġare": 601, + "Ġas": 454, + "Ġass": 947, + "Ġat": 514, + "Ġatt": 788, + "Ġb": 371, + "Ġbe": 499, + "Ġbe": 595, + "Ġbec": 706, + "Ġbeen": 686, + "Ġbeg": 915, + "Ġbetween": 914, + "Ġbo": 819, + "Ġbut": 623, + "Ġby": 473, + "Ġc": 368, + "Ġcent": 823, + "Ġch": 526, + "Ġchar": 822, + "Ġcl": 689, + "Ġcom": 509, + "Ġcomm": 707, + "Ġcomp": 616, + "Ġcon": 477, + "Ġcons": 841, + "Ġcont": 655, + "Ġcre": 931, + "Ġd": 387, + "Ġde": 627, + "Ġdec": 873, + "Ġdef": 965, + "Ġdes": 738, + "Ġdi": 892, + "Ġdis": 708, + "Ġduring": 864, + "Ġe": 421, + "Ġear": 854, + "Ġel": 869, + "Ġen": 662, + "Ġev": 682, + "Ġex": 539, + "Ġexp": 867, + "Ġf": 370, + "Ġfe": 845, + "Ġfil": 913, + "Ġfin": 786, + "Ġfir": 599, + "Ġfirst": 626, + "Ġfl": 877, + "Ġfor": 614, + "Ġfor": 458, + "Ġform": 963, + "Ġfrom": 503, + "Ġg": 430, + "Ġgame": 895, + "Ġgen": 985, + "Ġgro": 890, + "Ġh": 380, + "Ġha": 485, + "Ġhad": 566, + "Ġhas": 679, + "Ġhave": 667, + "Ġhe": 558, + "Ġher": 660, + "Ġhim": 896, + "Ġhis": 512, + "Ġi": 366, + "Ġimp": 909, + "Ġin": 429, + "Ġin": 389, + "Ġinc": 618, + "Ġinclud": 761, + "Ġind": 983, + "Ġint": 628, + "Ġinter": 832, + "Ġinto": 785, + "Ġis": 480, + "Ġit": 533, + "Ġits": 642, + "Ġj": 723, + "Ġk": 564, + "Ġkn": 857, + "Ġl": 398, + "Ġlar": 962, + "Ġlater": 936, + "Ġlea": 868, + "Ġm": 386, + "Ġmade": 949, + "Ġme": 968, + "Ġmore": 802, + "Ġmost": 910, + "Ġmov": 956, + "Ġmus": 966, + "Ġn": 415, + "Ġnew": 989, + "Ġno": 547, + "Ġnor": 978, + "Ġnot": 632, + "Ġnum": 926, + "Ġo": 359, + "Ġof": 373, + "Ġoff": 875, + "Ġon": 551, + "Ġon": 456, + "Ġone": 677, + "Ġonly": 871, + "Ġor": 699, + "Ġor": 645, + "Ġother": 787, + "Ġout": 925, + "Ġov": 729, + "Ġover": 856, + "Ġp": 379, + "Ġpar": 636, + "Ġper": 736, + "Ġpl": 698, + "Ġpla": 697, + "Ġplay": 808, + "Ġpos": 859, + "Ġpr": 889, + "Ġpre": 749, + "Ġpres": 912, + "Ġpro": 506, + "Ġproduc": 934, + "Ġqu": 955, + "Ġr": 521, + "Ġra": 863, + "Ġre": 400, + "Ġrec": 597, + "Ġrecor": 919, + "Ġreg": 943, + "Ġrel": 900, + "Ġrele": 946, + "Ġrem": 848, + "Ġrep": 762, + "Ġres": 650, + "Ġro": 629, + "Ġs": 361, + "Ġsa": 905, + "Ġsc": 732, + "Ġse": 569, + "Ġseason": 948, + "Ġsec": 781, + "Ġser": 740, + "Ġsev": 884, + "Ġsh": 513, + "Ġshe": 862, + "Ġsp": 578, + "Ġspec": 940, + "Ġst": 446, + "Ġstar": 939, + "Ġsu": 770, + "Ġsub": 969, + "Ġsuc": 764, + "Ġsuch": 981, + "Ġt": 354, + "Ġth": 355, + "Ġthan": 918, + "Ġthat": 452, + "Ġthe": 502, + "Ġthe": 357, + "Ġtheir": 621, + "Ġthem": 998, + "Ġthey": 727, + "Ġthis": 705, + "Ġthree": 902, + "Ġthroug": 923, + "Ġtime": 783, + "Ġto": 391, + "Ġtra": 836, + "Ġtw": 639, + "Ġtwo": 688, + "Ġun": 544, + "Ġup": 898, + "Ġus": 668, + "Ġused": 988, + "Ġv": 495, + "Ġw": 363, + "Ġwas": 422, + "Ġwere": 525, + "Ġwh": 443, + "Ġwhen": 851, + "Ġwhere": 995, + "Ġwhich": 573, + "Ġwhile": 935, + "Ġwho": 724, + "Ġwit": 451, + "Ġwith": 994, + "Ġwith": 466, + "Ġwor": 643, + "Ġwould": 801, + "Ġwrit": 937, + "Ġy": 580, + "Ġyear": 987, + "Ġâ": 556, + "ĠâĢ": 565, + "ĠâĢĵ": 631, + "ĠĊ": 412, + "Ģ": 161, + "Ģ": 223, + "ģ": 162, + "ģ": 273, + "Ĥ": 163, + "Ĥ": 262, + "ĥ": 164, + "ĥ": 337, + "Ħ": 165, + "Ħ": 278, + "ħ": 166, + "ħ": 281, + "Ĩ": 167, + "Ĩ": 308, + "ĩ": 168, + "ĩ": 225, + "Ī": 169, + "Ī": 221, + "ī": 170, + "ī": 244, + "Ĭ": 171, + "Ĭ": 315, + "ĭ": 172, + "ĭ": 321, + "Į": 173, + "Į": 324, + "į": 174, + "į": 302, + "İ": 175, + "İ": 249, + "ı": 176, + "ı": 332, + "IJ": 177, + "IJ": 295, + "ij": 178, + "ij": 313, + "Ĵ": 179, + "Ĵ": 328, + "ĵ": 180, + "ĵ": 312, + "Ķ": 181, + "Ķ": 256, + "ķ": 182, + "ķ": 314, + "ĸ": 183, + "ĸ": 277, + "Ĺ": 184, + "Ĺ": 322, + "ĺ": 185, + "ĺ": 285, + "Ļ": 186, + "Ļ": 267, + "ļ": 187, + "ļ": 290, + "Ľ": 188, + "Ľ": 311, + "ľ": 189, + "ľ": 299, + "Ŀ": 190, + "Ŀ": 291, + "ŀ": 191, + "ŀ": 293, + "Ł": 192, + "Ł": 335, + "ł": 193, + "ł": 252, + "Ń": 194, + "Ń": 297 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/unet/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..df1836184f4cbbbbea434a16537c7f43c2ec5ade --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/unet/config.json @@ -0,0 +1,119 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "addition_time_embed_dim", + "addition_embed_type_num_heads", + "use_linear_projection", + "num_attention_heads", + "time_embedding_type", + "timestep_post_act", + "only_cross_attention", + "time_cond_proj_dim", + "projection_class_embeddings_input_dim", + "dropout", + "class_embed_type", + "attention_type", + "time_embedding_act_fn", + "cross_attention_norm", + "num_class_embeds", + "mid_block_only_cross_attention", + "resnet_out_scale_factor", + "encoder_hid_dim_type", + "addition_embed_type", + "encoder_hid_dim", + "resnet_skip_time_act", + "transformer_layers_per_block", + "conv_in_kernel", + "dual_cross_attention", + "conv_out_kernel", + "time_embedding_dim", + "resnet_time_scale_shift", + "upcast_attention", + "reverse_transformer_layers_per_block", + "mid_block_type", + "class_embeddings_concat" + ], + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 32, + 64 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 2, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "unet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 32, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "sample_size": 64, + "time_cond_proj_dim": null, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "transformers_version": null, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/unet/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/unet/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..d4f8db4ef3d3c34b1b17a814bdfa12106d0c5aac --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/unet/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de94ea057ec448605dd805e4abb330c25a05b5682b5d272c21766f7ba9e37447 +size 5593017 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_decoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_decoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f0afd59fb5c2bbed6cf7ad6c312f8e6ff16c6815 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_decoder/config.json @@ -0,0 +1,64 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "latents_std", + "force_upcast", + "use_quant_conv", + "use_post_quant_conv", + "latents_mean", + "mid_block_add_attention", + "scaling_factor", + "shift_factor" + ], + "act_fn": "silu", + "block_out_channels": [ + 32, + 64 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 1, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "vae-decoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 32, + "out_channels": 3, + "output_attentions": false, + "sample_size": 128, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_decoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_decoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..de149be7e4cd6baa1c204013f35681d362d252a5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_decoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3100941118e98b5c58d65a627dba91267dab977ea980d9083c03f4837f0d6626 +size 1905075 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_encoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..f7848ce5925bdd4fbd18d264a6b478a433febc65 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_encoder/config.json @@ -0,0 +1,64 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "latents_std", + "force_upcast", + "use_quant_conv", + "use_post_quant_conv", + "latents_mean", + "mid_block_add_attention", + "scaling_factor", + "shift_factor" + ], + "act_fn": "silu", + "block_out_channels": [ + 32, + 64 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 1, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "vae-encoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 64, + "static_num_channels": 3, + "static_width": 64, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 32, + "out_channels": 3, + "output_attentions": false, + "sample_size": 128, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_encoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..a3bc1710fa517a3de0401c8c35a5af2e768b4d59 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73e765061ca0edc0984c/vae_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac14c9fbde7a140ecd65238f367942e410e6701eca1467aebff6032338d52ec8 +size 1441395 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4bf48cedebf320b0c5081c9342d4238acb70fdfd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87551c425d5a4545bedd0afacddec45628d5eb93d3733f6b3b09bc48b411558e +size 220920 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f559e728fcaf36648fdd1a831c37af68eedda81d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90bc5ec65ac5275b84c82d6342a170e6ea1dc1172b7e496f0d7c3e2272d4394a +size 246784 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..789667eb41ab8c8f609b3b7a0c8a7f08d727e2d4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_73fde5a38839e503faa4+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:376d6c47055c7a84fc8865ddef4c63c9e23aae2eaecee00e437a75966b727c39 +size 254997 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a9a293bdb3edb3452870d84cc0778c319a9980a8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f027d584872203ce72aa85a5ce96f38c9cd5a63158615ae79ffd1b054d29c9f +size 1759769 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c291113b25c7f74b85cb526908d2a61a752fd071 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_797a0d607acbacd73bc4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:563fbed6e37d0d9a0513b1ffa2801bea461eb09955dcbc5b19786ec94b3faf86 +size 1731584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1354affcc3c26a02c3e16d01f94b92f0c84e3491 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2c544c43fdab8a0527349a1afb3bb9521067467764580366164539614f0c50e +size 4038366 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..98e3ad46ea635c84b9766068da533622e995ba92 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a143e9f44ff22eb2801+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71b067f737ed22ffe7dd7cb6a1487f691f9dfecd8b123be24fc917f9e00eff4c +size 12145664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..79f5c94894f18a12cf3620658159a4ef25768402 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d05458ab59fc6f2531999e17b25b84162b3edc4ed6a749d613fe97e90d9f413 +size 2769120 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c45f3640b94ac8a3186e6e153d74aa2c2bc42dd0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7a5ae276c555d2c5222b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddc992616eafca636560202912d0d0e2246b5ff16d54e285b6c31f2cd774ab2c +size 7834624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..36615c194fb57eb5d9e78051b9ec4a16ca62f7eb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39b7ba1127bfc41686fb54dc57c2758b391f6aad3492602e41466de6adf73faf +size 3259197 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5a7dc93e282c795223c50a27fecfb73fbe814868 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7b01a92f1a36b7b0844c+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e8c07bd40ff0e35e7261bd3d74350abffe919ffbe14052c05e7115adde9c925 +size 3318784 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7b41c3faa6c85fefc5efc23c5c5ddb6a4e96c3c8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df180c101230477ff5a4567ec92763d8e066a958b672201797236c61065a44d5 +size 4081300 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..80b0d141233cfe0f114e3079a523ee0ef80fb7d3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_7dcec5e93455378688b7+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:813e2777a5a256c5307460acceb9499f8cf2b1897c05fe33c1e5d6f761353650 +size 12145664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7f480b372338617bb2928fedfc1ecdca00c7aed4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96753dad43dfc3a75700f4ef14fcdfe3710cfdf332bf9e8a664c8828f169c75b +size 3260631 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f4a261cfdc2d6bd66949503b8b769d497bc88d67 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_81ca1e738749cede64f5+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0883b04b567d807b29cca66aeb461e8f66cb7b49d711df5153a2da3e7914a3a +size 3318784 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d76fa9ec688cbf448a956bfef6d7337636c36b23 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d4b30379119afa7c317ce549f31dea8ff60b69f9b50d240c56f15dac62d5b0 +size 1884047 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..71b446e3ae068ff6d686e546d14946ddb85b0bf2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b26c0f21520c377ef6b8e6a24d9e8889e813e916edc5274a82fd58031759a5 +size 1158144 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..4ed782c8050c2df5de60d70c1c0f07b2728a6b5e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_84fac9181b5d14db36da+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5218186bb4a790018c9c9f523c65d0964cc7942a7750496dd2f69d31dfde6242 +size 1280533 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..88b44446245646668212f7f5490735f1b32e5842 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e647593ac79f1aad7b98176515c1c2b6e589d704e2f2dc48c51bebfaa4c43f56 +size 1437353 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8373d36db7a073591b3447b8655cef0494c9a433 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcf7ab149507a1959fee6bb162328ec57acece883c6e20806d513b862054a62c +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..fcfbc65eded9426b298ffe1b13bbbc1d3252bd89 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_850d83edca7646932466+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9651465fb64d85368fdbc48eb2c00af128668c2dabff4b50560a805bec46fa67 +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a8c72fe9f6b121cab8763422030346dbbdd1cbd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2340b70dfa47166d1df502e73cb5b1acdc307eafde959caa31f2f91cf94498b1 +size 1844527 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d5a4e4b96b2d03ea8cb039944e4e4b2f627da5c4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afdbe5da4f8dc160c4752e0c39699931aa864ce9e8ae2a41086a81281b416fe2 +size 1373184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5fe9b06375c73ee82538c8d3653f2796ab0b10cd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_885370837f47156d6058+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f246b3e78ad83fb93fbd374dadb1472cb102c966baabf7a52b4376a76d013d46 +size 1495658 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..236b480fb7c0a79a03982b100a6bbea67b2f12a9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9429fda17fc08d5991b6747d3a9866e6057084601ec96f814422ce5d4f5f815a +size 1885339 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..77fb56eb481c409c010f4a76a6bacd532426d8ba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7305ecb7a68336d5bf97c158223363289e613caa66e19683db7ba3ae598a5a75 +size 1342464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..f331514b67f62883c7b6a6b208d9f5d6509d03b0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_8b9a3de21061e9ecce8a+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e0e92e99c312a2d599e033dd9f271ad7d700556f5a0446b9db54aeb9ed31cc1 +size 1464853 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a7cbcbf5ae271f796fe03339aa5056956dc0a611 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c89614bb24b5de480574220c100597fd203a9ccdfd1929fa4d97841f398da718 +size 1841801 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4cc6953c0bade76dd74d76b3f46b936afc74366f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15ea6bcf0b6fcd0e285a976a0356c6a0fb3f8ff7f96ad3e66290032ce7912c54 +size 1342464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..0c95da3888670fb8914c59a55917222a60bff47d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_93ed16e7c6730242b94b+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:999a10be3d2890310776ff3e23d14ce727e1cda66c8e0fc1382f31161ab7c9b2 +size 1464853 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..44cf2d7653076513366c1ed9d46458ebb2e6d15c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8cb9ff0787d894907bfbf20e07a3923f6612e2c3f7a8660848e549e71549b98 +size 3662639 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b3eb559ec3c61b1c001b9f7b78f49b8fd77c1127 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9fc567a34e7dd6c19fea3f7efdc65c34c7170eabf9cd8f9955e2663fd8ab26e +size 4936704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..46e856ca53df58ddc25344d6fb034cca12d86a1a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_942cb41a25c886b376c6+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32451aa5aced506718c1d6a7cd18e5bb12e5ec39ce4ee3e20c42b3b50c285559 +size 5121163 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..315c8191f71e424b327560d025a0e9a2c8c8acbc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2adc94e07de4417b83d1ed8ade2b1c65b12d505f70d739bf22c3ec484730daf +size 2677785 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d7aeee6f2fd4c8051f3726dfed3db6c53b326d23 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_943e620ba286661d8173+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dabdfe267a906d3146bca221668312af0dd9c9cba4898fd7340432d542ad702 +size 2868224 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..21bbde05fbd71049a52c508c3bc08c6d1ff30d38 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2d3036628953271e346813b37c3607ed18d366b1a29c0425951adbaa1d0cfe5 +size 1457297 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a4865572b86fac9cc57855c9b39917bc4020ea11 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bde8a1c47b910fdf6d6fed3a4767620a9b35e73afe3bc69ba41e92bcdf2a2c5 +size 2305024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..bb4636b59b41411d47facbd5d21246ba304058b6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_95b2a9888763feede71c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d703ab20f5c5397918486f95219e30849c19c234ddbe65a569e8303908e3bf +size 2379111 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9637a8418978fd74f1836f815e9bc6a9dbb32800 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/vision_encoder/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7c2e9b5371affa210d47e0bffde7e23620fa13b8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80f068639fe8c5ad489f0932602f607772bbf06cb38b503fbb719d8d20fbd374 +size 1847925 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..61c5aa296e63f4263b8b168c58c519f59090a1d3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86c9cf2f2272055ee9545ee25366cd0fc8af2164b4958c5a1ea84bc483b58a6d +size 22928384 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e00cefaba5fba2ef3377218853256ebe261d12f3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_96b0595fcfb688e22991+1d5aa319/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d30dc8f831b3c60d6e159b8d1906ca52ab5e763213920f793a0e1440c439f1a +size 23161502 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7c616d3144de21a360ed9249d5a9953bf049981c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:155fcbff4227fe3c6dc8e177a58a7762d9636bb82fc3bc5b07288f8bb35530fa +size 2022219 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b2a3b76f22ebaeca566f07b0f186a9d6b62edd91 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97e2a10e28dc6c0ad008+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ad32ea7daf208d145850fafe52f55964f89979ab47fdfd003e2ae05147b605 +size 2970624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..26ea14f9f76a992f8b09d52b6486804fed0fc888 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0fe068dfaa913a97916fcc2488c5c77f80b191650b15912139178c1b0707b736 +size 1648464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a65fdca8029e1dbc86a98c4b3a03185697b2d333 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_97ffaf0122e932464dcd+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6939ca81ce4fce547b9afaa9f2f660351b9ab390610b49a80e0e3d2bfa476905 +size 8336384 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3d36ad5ba666ae32c6df1ec5538a334ca5ebbffe --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80d764183f58f2092b42b7f533a326bff75b09c9a1a8e904e4eb82e2f190c5cb +size 2027971 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a1497bb2577d716e1d1af803669775f73ec2d2f9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9e9ac2ab5c4f2d067d64+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:567412fabfa7a14b5acffbdc8d6bf2042bb091c5f6ad5990fd8e87dde710fa6e +size 2970624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1b770bac35753c4c2857fc9f3f1cfc3f0d48a2bf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f18bf18dd710dc60bcb341d66f848c84aa4dbefcf38d8b13d3b1911012ca8e80 +size 2034351 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..6002c079409026b330487fac06bb02f06206c8d2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_9f565ecac6bdf7c268d0+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:307ed8ba0255050c7dc214efe54a2640728172559ece8aafbd7b07e1ca643571 +size 3410944 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..06a4b0b1375ac20a363c9eb750c1e228f0e9d8fb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f91c26358e5e6c2a33310a7b60dc6ae70ecc8bfead00a7564ccc2496cfeea63 +size 3300342 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ada8c6f4042d09d268dab7f54857e4937b824f25 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a1da31d69d33b0feed0d+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35ed738405679222db0d1cafdbe655fad396f25c3ecfce4d42f47598f1663d4b +size 3318784 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d6aaead6d5e3c59f3170b3ad202f9960aff966e3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98055c49397a3de318c5009e9aa8b90640e274eebd40dba4b6ba363b1a770b85 +size 1199160 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..da74fcd74ae37ec20257e5e5602ad8eda9797ec0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a38d59aa68f454800914+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3bd9dc78b065ec5208f145413bef85f84ee5c7d1b9d7927d92982f48d63651b2 +size 5213184 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bf18cbb7aa286745cf3e29e039d6df71265d1b81 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ed3df54747d372ece6d3dc8bcdf1d495081f844af02d4cf026657ee7a004d81 +size 1282460 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bb9f72fd33eef657de8910bd7d10ad2d9fd0b772 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_a9abbb1d2ae349f44e9b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d8b4337c30c92f74fb633edf7bd80fe9fed31f816305452d7aac6263890fdb5 +size 3267584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..36de1273a2ace69da810e15ba2a6000b8de9b38e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1392661f24d45a7a1652be20d314ad0ccc9d37523199eefca58f3e2ea5b7d8cf +size 1853766 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1bad628ac5a75c8a5c1a9159aeb45b186ba089a4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1817c08a1990b65065361758d9eed9c417a85f79e38a710c3ff02bbf6583512a +size 1342464 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..93d98461434863040e06c426235a24b350892dbe --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ab49061cbff5ac26a535+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:466030bce7b3aed562b4f5aa9c64eb0275368bca43ef3e90b644220035836cca +size 1464853 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7b4009d41f46baa14147fb9d234c59d0aef4637c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3aaa80fa56846e4f3b99f8df97198b887b5e58ff90defd918e87afa9e200843b +size 2984271 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e3a38646270dd72a680c4c782cac7592adcb61a5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_adb9128be89a1c98b633+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6212901312ec3fff5f58f74bd9e63a9a0069b571dd76d220a243d07e30f77e65 +size 15371264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e786090152d782ed56cc142e2e3095e95f458cf6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee3f7b7d7bb3893c3decd601de3fe7d07b6dfc943bb1b1b556665e3c1610d750 +size 2257212 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e304a59ca12314b52dd1652a363fee8f85c18a53 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:911e4c23509771ed88cf142eaad90c3268566024b93a9d2e5c8b364017476d68 +size 3277824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..e32df5f504686a3cb3f3e34d486973a245040106 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_addb5aa6d184bf31c794+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c62e751a7509670fd4668089a175acaaf6fe2e335cf17e8e3798393aa085b5bd +size 3415603 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3548288c8824f7f9451194c210724d037f21ee98 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b6099ab52340b854f8b809db7ad6fb77e4d74a6a96886b57ccb3fa7ffac1f86 +size 1449548 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..83dd2e5cf38afa32d1ce0989bb7157f3da5cf606 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ed4f988071fb38fc07a397ff7ebeffc1a1d2025209c940f7d1fde51b3263ea +size 2305024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..87f782f5a9ef44ea498b2f330da6df9f4429a64f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b209dc66669452006807+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6a29e24ee3aa8b5f7b4f7d3c441ecfbe10eedb226b546e6f9d43ad70c898c60 +size 2379111 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b8dd23fcdabf8e5bec7ddc689e5067e18627b732 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e9b2541b9551cce45fc10d0261cad481475a5b858e21709411315ca8f926cc2 +size 1446378 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ee807de1037fa32197745425b4d49b347d5221ee --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:793e766c19e8e8813977af9772c63878f3530d53a384f18d1d4fb14d8c7d1d35 +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9942528622de7ea966f5f5cf2e2c61f8f6023c10 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b352b056488c703f91b4+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5fbc2e86d8ecd623ce7177666e922f2694710249fce24b74fb00106f580c016 +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7820917fc513ba3009235bac58c4ce9d12b8edc4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf9d9ffdb58680835338edf71db0dda7f00d1e9c451de0c5f961a822578eee62 +size 1296901 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..72c55269a46358af2bb29d82a13fd5ee36c99be3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b4d25e616296d9d065d7+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0406aea316fd3966b0b93256cc6e7127c4399108e5d58220650044aedd48a54 +size 3267584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5e70afbe088557f3a077f82feab915da792cf4bd --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92b6a313c1818c8f26362b75149807f85ae573cfa8b14fd2550f8bc2c1d9d605 +size 3674500 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f032af98dedd599ac15d3b3d025318b9a7f78b20 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a68adf58e604c39082750cd17609f7d95c3c5dd0d1e1172e8109e05f7ed91e9 +size 5131264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..246fd896adc10a12b2610c7121c22fcf6e336abf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b6ba419c618014159090+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70eef66e8fe373b509cf78b9c0fdcfe87852323073d917844338a807b42c6c5d +size 5315443 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..44d357423a3019177f27b7b0fb7f9152b46bcee4 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d56785e933048c814d1d85b276852e2918d67ffaa7c3855d29317e404e691a1a +size 2143615 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..134ab69f4bfa222bcd13a94f8eac40d4653bb1d3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4765cee9774325ad246765c4a493d555b5b07ecbfcc4b8bd5b9c9dd2d0503ee4 +size 1649664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..3e35e023b3c5114f435c75f131fcc91846f56331 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b87d2eedb0cd1b974d71+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18ad200146b3c928a559a5dd3a9b6d4851baec2b08718f5f8a886de812b88c7 +size 1805855 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..7e82624a5e3ad8a4d4767dc36d6cd5b769a01d9d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8395a8ab7ca8abecd0bc25e05ee46ccb8b48de7672512f0982d88694c13c029f +size 3707575 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f0fd881376da57e3b862ee4f2764d1955148b834 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee50344509723e61338e4529bdabed7b842c3611a72e9958b00dff8aa480df68 +size 5131264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..47d4d397106aed806927fd08ad6b1c29f7c95948 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_b91ae604eae60b0fabf2+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99ebd0dbf59439da30b66b07d5b09eeeb451cf3c2e20508782d05956eb5322d6 +size 5315443 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e855517ee7706456576b0bf39aaa89058f25e5f6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b855b70efab9b0e769db7566b989e172a20afd8f42ad00f665be41fda50b3a7 +size 2948312 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..38831733415f5e28b6a2833a96ebbc20548602a0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ba3b564583f21557a4a9+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3b9e9e3b0f8829f085e53c7334450df992e1cceccdd81df57fb982255ad3c74 +size 15361024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e8c6d9e3d13bbcc7cab4af07d24f620cbf8345d2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e45465e1b2670b1f46b939868a7befe573784636302a3be905298203f680146 +size 2238632 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55d1f6f45e5e991d69f41a63b21a8025d893bb79 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78df1c1b8224502b5e5aa47be92c02bdf4a631591b18c1835c64dcbce9120ea5 +size 1700864 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1f15c48c7a6e1eaa4dbbbcb74472a83b80135a6c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bd61d5d24b04539e47bb+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94031d1303ea4d5637cd9f3868ee9537cc0363528bc3d1c03c5f0c476cdbb815 +size 1857170 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d84fb4f20a6b4ba739533518b2bc90aaf1d82312 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82d44c889a3753fa7589ac216ad9a2df194384f05a7de7be8c250c86e35fb50a +size 156253 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..dffd62a90c9ecf0d5b26e97fe02cdb4ced4448d9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_be22190e9ba1805e0bbd+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb850d50a75f52890e4262c645a6424c79da8881051a2e092547f2d027a28364 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4e02997224e7aa380fdcf35216ca7086fd9c0370 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:040d72efb0c349ba44092c3f5ae8a9a73cb3ac93f803290e39c7c6b9082464fc +size 2984798 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..741d92323d671ecdedc5e611f68369f31f62bec1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_bead9853fbf8905491da+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60e33e401beaa73f1a5c0a796169526bf4d43ede1d33b73f01912af7d9ccc88 +size 15371264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..8549106aeba9c7f9bc601beac3eb609336c57cf7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edb295fdf88e9409db29f68fdd4c8e90a62a016bef7e6f5b83895dc46f88b809 +size 4892242 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..094f3b773d9c5113a4d83e46d0f55f7aa14787cc --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c0eb50bfe337a2ae0eb6+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e968de70bdf2fa5f9bb34998de8cc74d64c4a595008bdb00aeee1668221652 +size 10957824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4d3e699520f02473850dc8599371e00afab3c6f9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc88bf00477a6a61081e82b3f32132a65f62c906ceb5076093e0bb4430143c3 +size 3691547 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..46b2dc77805d3adbf7b08880d4f4c4da07e79889 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70536a2499519bf71bb61faf919707d06b59b4f14033c2ae4043d7c7a9d46741 +size 4936704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b2d663de738c1dc7da39515a172454d8f92c1fd6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2339f7dfd92bc4f4a09+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a89ff9d3e573007fc1a25d3776732db8a5e781e0e865e0970e0d8e86196ae5da +size 5121163 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b5c88db8ad1a1c7f12f79a21e4bd0a291379cfef --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ee21c04b5827f601b958451f9d037e557907dbf1572cf841398dd810d91d6e +size 3524690 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4af4c756d0b07b2ea967d187eeeaa7231bf90a34 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58ece749a67908627e91828706bb90f3379040bef43be3c45a3fb5ed106ab573 +size 6657024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..43f4166969d617e6b6de47338d418335d5d1c73d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c2719f909b7994638732+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1321b543910253642ed20067a09a932fb4b585aa793bcc448a9ffcc4407027c +size 6887798 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3feaf602b0dc50985b108d9c7da298de6f9cfa91 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:797329982467a162c19efaeeaa75937e3accdd18be933c02336ccdfacdd000ea +size 1448425 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..5c17963caa5e27705a64b13a62e4dea2902c9beb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40658abe5395053d801809c6ac05589b4d010d9830fc7d1d86e187f0877ada3a +size 2305024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..b78747d6aed9f7d618c24ef06d3b606dc5820add --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c35c1d0c26d1633c765f+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738144efe14e899cce65bba9514fe34fa1d3a4cd07105825e34697249ce1663b +size 2379111 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/feature_extractor/preprocessor_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/feature_extractor/preprocessor_config.json new file mode 100644 index 0000000000000000000000000000000000000000..fb1692ff11ed6b3dee0634f577193bb23c0d37ec --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/feature_extractor/preprocessor_config.json @@ -0,0 +1,27 @@ +{ + "crop_size": { + "height": 224, + "width": 224 + }, + "do_center_crop": true, + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "CLIPImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "shortest_edge": 224 + } +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/model_index.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/model_index.json new file mode 100644 index 0000000000000000000000000000000000000000..cb57fc57957bef60dffbc280898a42e1fb2b979a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/model_index.json @@ -0,0 +1,38 @@ +{ + "_class_name": "StableDiffusionPipeline", + "_diffusers_version": "0.35.2", + "_name_or_path": "echarlaix/tiny-random-latent-consistency", + "feature_extractor": [ + "transformers", + "CLIPImageProcessor" + ], + "image_encoder": [ + null, + null + ], + "requires_safety_checker": false, + "safety_checker": [ + null, + null + ], + "scheduler": [ + "diffusers", + "LCMScheduler" + ], + "text_encoder": [ + "transformers", + "CLIPTextModel" + ], + "tokenizer": [ + "transformers", + "CLIPTokenizer" + ], + "unet": [ + "diffusers", + "UNet2DConditionModel" + ], + "vae": [ + "diffusers", + "AutoencoderKL" + ] +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/scheduler/scheduler_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/scheduler/scheduler_config.json new file mode 100644 index 0000000000000000000000000000000000000000..859e34ce893f24f014bbbb24c3abd335ed0ddc3e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/scheduler/scheduler_config.json @@ -0,0 +1,21 @@ +{ + "_class_name": "LCMScheduler", + "_diffusers_version": "0.35.2", + "beta_end": 0.012, + "beta_schedule": "scaled_linear", + "beta_start": 0.00085, + "clip_sample": false, + "clip_sample_range": 1.0, + "dynamic_thresholding_ratio": 0.995, + "num_train_timesteps": 1000, + "original_inference_steps": 50, + "prediction_type": "epsilon", + "rescale_betas_zero_snr": false, + "sample_max_value": 1.0, + "set_alpha_to_one": false, + "steps_offset": 1, + "thresholding": false, + "timestep_scaling": 10.0, + "timestep_spacing": "leading", + "trained_betas": null +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/text_encoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/text_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..2f1308f099b64ce0e1844dcb80c4661006e84eb7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/text_encoder/config.json @@ -0,0 +1,45 @@ +{ + "architectures": [ + "CLIPTextModel" + ], + "attention_dropout": 0.0, + "bos_token_id": 0, + "dtype": "float32", + "eos_token_id": 2, + "export_model_type": "clip-text-model", + "hidden_act": "quick_gelu", + "hidden_size": 32, + "initializer_factor": 1.0, + "initializer_range": 0.02, + "intermediate_size": 64, + "layer_norm_eps": 1e-05, + "max_position_embeddings": 77, + "model_type": "clip_text_model", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "clip-text-model", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_sequence_length": 77, + "task": "feature-extraction", + "tensor_parallel_size": 1 + }, + "num_attention_heads": 8, + "num_hidden_layers": 3, + "pad_token_id": 1, + "projection_dim": 512, + "return_dict": false, + "torchscript": true, + "transformers_version": "4.57.6", + "vocab_size": 1000 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/text_encoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/text_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..d1fa1dc484059180ce6d4ce26f581afdde0135f8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/text_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8787d2866fdda415d1c3ea5dd2c7a62e9c4f750f707b2da55091abe5e1603c14 +size 772787 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/merges.txt b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/merges.txt new file mode 100644 index 0000000000000000000000000000000000000000..e9193d6fc11f7b6e281b4686221363b6cdc4e576 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/merges.txt @@ -0,0 +1,647 @@ +#version: 0.2 +Ġ t +Ġt h +Ġ a +Ġth e +i n +Ġ o +Ġ , +Ġ s +e d +Ġ w +e r +Ġ . +Ġ i +r e +Ġ c +n d +Ġ f +Ġ b +a t +Ġo f +e r +e n +a r +o r +i t +Ġ p +Ġ h +Ġa nd +o n +in g +a n +r o +Ġ m +Ġ d +e s +Ġi n +o n +Ġt o +o u +i s +Ġ a +i c +Ġ T +a l +Ġ l +Ġ = +Ġ re +Ġ " +e s +Ġ S +a s +a l +i l +e l +i on +Ġ A +Ġ C +Ġ 1 +Ġ Ċ +u r +ĠT h +Ġ n +a s +Ġ @ +e c +o m +a c +Ġ e +Ġw as +Ġ M +o r +a n +a m +e n +o l +Ġ in +Ġ g +Ġ ' +Ġ B +l y +a t +i v +t s +ĠTh e +u s +- @ +Ġ@ -@ +i s +Ġ I +Ġw h +i g +Ġ H +Ġs t +o s +u n +t h +Ġ P +Ġw it +Ġth at +i r +Ġa s +e m +Ġo n +r a +Ġf or +Ġ R +e t +o w +Ġ 2 +i d +Ġ D +l e +Ġwit h +l a +en t +i m +Ġ F +e a +i on +Ġb y +Ġ ) +Ġ ( +Ġa l +Ġc on +en t +Ġ W +Ġi s +er e +Ġ G +Ġ N +Ġ L +Ġh a +er s +r i +t h +t ed +u c +Ġ J +Ġ1 9 +e v +u l +Ġ v +c e +at ion +ro m +Ġb e +Ġ E +i n +Ġth e +Ġf rom +Ġ O +t er +Ġp ro +Ġa r +a d +Ġc om +i c +a g +Ġh is +Ġs h +Ġa t +o v +i es +o o +p p +s t +c h +Ġ r +Ġ2 0 +a y +i f +Ġw ere +Ġc h +u t +s t +u t +d s +o p +u m +Ġi t +o c +t er +l e +ig h +u d +Ġe x +ion s +at e +it y +at ed +Ġ un +e p +q u +Ġn o +Ġ K +iv e +is t +Ġo n +am e +ou n +i r +a b +Ġ â +in g +Ġh e +l d +u g +ic h +Ġa n +e d +Ġ k +Ġâ Ģ +Ġha d +v e +a in +Ġs e +t ion +or e +re s +Ġwh ich +ĠI n +o d +th er +a k +Ġs p +a r +Ġ y +ĠC h +on g +Ġa c +es t +Ġ U +a p +f f +al ly +r it +ĠS t +u b +g e +b er +e t +Ġb e +e ar +Ġre c +er s +Ġf ir +o t +Ġar e +Ġa n +c h +o g +i a +es t +in e +il l +an d +e l +ar y +e w +i d +Ġf or +Ġ ; +Ġcom p +Ġ V +Ġin c +t r +Ġ20 0 +Ġthe ir +u s +Ġb ut +r an +ic al +Ġfir st +Ġd e +Ġin t +Ġ ro +s o +ĠâĢ ĵ +Ġno t +d ing +f ter +ur e +Ġp ar +Ġ : +i an +Ġt w +ou ld +Ġal so +Ġi ts +Ġw or +u m +Ġo r +os t +0 0 +ou r +ar d +Ġre s +m p +u e +Ġa b +is h +Ġcon t +Ġa d +ow n +al l +ou g +Ġh er +as t +Ġ en +om e +al l +d ed +o w +Ġha ve +Ġ us +ea r +ac k +d uc +i al +s s +en ts +a in +t ing +Ġon e +es s +Ġh as +igh t +a v +Ġe v +ou t +a y +en ce +Ġbe en +e w +Ġtw o +Ġc l +d er +im e +k s +es s +is h +. @ +Ġ@ .@ +Ġp la +Ġp l +Ġo r +u p +m ent +ur ing +ol l +ĠI n +Ġth is +Ġb ec +Ġcom m +Ġd is +at er +ag e +Ġa pp +ou s +e y +i l +p er +ĠA l +ion al +l ud +el y +t t +il e +i z +Ġ j +Ġwh o +Ġa g +i b +Ġthe y +f or +Ġo v +at h +e g +Ġs c +i p +Ġ20 1 +Ġ 3 +Ġp er +or y +Ġd es +id e +Ġs er +s e +ĠH e +la nd +at ions +r ic +i t +re s +er ed +Ġp re +ĠS h +an ce +or t +an t +, @ +Ġ@ ,@ +el l +Ġ Y +n ed +el l +it e +Ġinc lud +Ġre p +Ġa fter +Ġs uc +re e +an y +i m +or t +Ġ1 8 +Ġs u +ad e +ou r +ĠU n +ĠI t +i k +ĠM ar +em ber +Ġ 1 +e en +a nd +Ġs ec +ic e +Ġt ime +ĠA n +Ġint o +Ġf in +Ġo ther +Ġa tt +il l +re n +ac h +as s +er al +es e +s h +al s +it ion +oug h +l es +am p +Ġw ould +Ġm ore +ro ug +ri b +er y +ac e +Ġ A +Ġpla y +it ed +k ed +is t +i ed +Ġ 2 +as ed +ing s +an g +a m +i p +Ġb o +ab le +t y +Ġch ar +Ġc ent +et w +at es +ro p +Ġ I +u nd +ĠA m +c es +o in +Ġin ter +u p +c t +on e +Ġt ra +an t +ec t +Ġal l +e f +Ġcon s +ub l +n ing +an s +Ġf e +us t +Ġ 0 +Ġre m +as e +on g +Ġwh en +e b +ĠW h +Ġe ar +ev er +Ġov er +Ġk n +a us +Ġp os +a d +er m +Ġsh e +Ġ ra +Ġd uring +as on +v i +Ġex p +Ġl ea +Ġ el +Ġ 4 +Ġon ly +o nd +Ġd ec +Ġac c +Ġo ff +is s +Ġf l +ĠE n +o t +en s +os e +ak e +o m +Ġs ev +ac h +etw een +er n +Ġ 3 +Ġp r +Ġg ro +r uc +Ġd i +Ġ19 9 +ĠA r +Ġg ame +Ġh im +oo k +Ġ up +Ġab out +Ġre l +for m +Ġth ree +at t +ĠC om +Ġs a +ear s +Ġ 5 +r y +Ġi mp +Ġm ost +f er +Ġp res +Ġf il +Ġb etween +Ġbe g +p h +or s +Ġth an +Ġrec or +o b +er ic +at ing +Ġth roug +k ing +Ġo ut +Ġn um +oo d +oll ow +ac t +u il +Ġc re +ol og +at ional +Ġpro duc +Ġwh ile +Ġl ater +Ġw rit +e x +Ġst ar +Ġsp ec +e e +ish ed +Ġre g +is ion +ou th +Ġre le +Ġa ss +Ġse ason +Ġm ade +il y +r u +o y +t ur +t e +Ġ qu +Ġm ov +ur y +ĠAm eric +em ent +c c +ou nd +Ġl ar +Ġfor m +ec t +Ġde f +Ġm us +ĠP ar +Ġm e +Ġs ub +w ay +o p +o h +el d +i e +em p +am es +er n +Ġn or +iv ed +ev el +Ġsuc h +ar ds +Ġin d +ik e +Ġg en +er t +Ġy ear +Ġus ed +Ġn ew +Ġ 5 +Ġal b +s p +y p +Ġwit h +Ġwh ere +ic s +ĠTh is +Ġthe m +w n diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/special_tokens_map.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..cf0682d6de72c1547f41b4f6d7c59f62deffef94 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/special_tokens_map.json @@ -0,0 +1,30 @@ +{ + "bos_token": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/tokenizer_config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..e2c6e161507ea47b93cec9528dc3e093b4d672d9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/tokenizer_config.json @@ -0,0 +1,32 @@ +{ + "add_prefix_space": false, + "added_tokens_decoder": { + "0": { + "content": "<|startoftext|>", + "lstrip": false, + "normalized": true, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "<|startoftext|>", + "clean_up_tokenization_spaces": true, + "do_lower_case": true, + "eos_token": "<|endoftext|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 77, + "pad_token": "<|endoftext|>", + "tokenizer_class": "CLIPTokenizer", + "unk_token": "<|endoftext|>" +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/vocab.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/vocab.json new file mode 100644 index 0000000000000000000000000000000000000000..609c08ebb708079189a79c6964c3495e36b26f41 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/tokenizer/vocab.json @@ -0,0 +1,1002 @@ +{ + "!": 2, + "!": 345, + "\"": 3, + "\"": 344, + "#": 4, + "#": 325, + "$": 5, + "$": 348, + "%": 6, + "%": 351, + "&": 7, + "&": 352, + "'": 8, + "'": 296, + "(": 9, + "(": 318, + ")": 10, + ")": 330, + "*": 11, + "*": 327, + "+": 12, + "+": 341, + ",": 13, + ",": 279, + ",@": 754, + "-": 14, + "-": 276, + "-@": 439, + ".": 15, + ".": 253, + ".@": 695, + "/": 16, + "/": 350, + "0": 17, + "00": 647, + "0": 216, + "1": 18, + "1": 222, + "2": 19, + "2": 231, + "3": 20, + "3": 243, + "4": 21, + "4": 233, + "5": 22, + "5": 240, + "6": 23, + "6": 226, + "7": 24, + "7": 215, + "8": 25, + "8": 236, + "9": 26, + "9": 242, + ":": 27, + ":": 353, + ";": 28, + ";": 317, + "<": 29, + "<": 340, + "<|endoftext|>": 1, + "<|startoftext|>": 0, + "=": 30, + "=": 342, + ">": 31, + ">": 300, + "?": 32, + "?": 346, + "@": 33, + "@": 320, + "A": 34, + "A": 227, + "B": 35, + "B": 258, + "C": 36, + "C": 239, + "D": 37, + "D": 255, + "E": 38, + "E": 246, + "F": 39, + "F": 213, + "G": 40, + "G": 283, + "H": 41, + "H": 219, + "I": 42, + "I": 237, + "J": 43, + "J": 251, + "K": 44, + "K": 254, + "L": 45, + "L": 218, + "M": 46, + "M": 234, + "N": 47, + "N": 238, + "O": 48, + "O": 265, + "P": 49, + "P": 245, + "Q": 50, + "Q": 309, + "R": 51, + "R": 264, + "S": 52, + "S": 230, + "T": 53, + "T": 235, + "U": 54, + "U": 268, + "V": 55, + "V": 248, + "W": 56, + "W": 274, + "X": 57, + "X": 263, + "Y": 58, + "Y": 310, + "Z": 59, + "Z": 207, + "[": 60, + "[": 270, + "\\": 61, + "\\": 338, + "]": 62, + "]": 289, + "^": 63, + "^": 331, + "_": 64, + "_": 334, + "`": 65, + "`": 347, + "a": 66, + "a": 197, + "ab": 555, + "able": 820, + "ac": 420, + "ace": 806, + "ach": 791, + "ach": 885, + "ack": 670, + "act": 929, + "ad": 508, + "ad": 860, + "ade": 771, + "ag": 511, + "age": 710, + "ain": 568, + "ain": 675, + "ak": 577, + "ake": 882, + "al": 397, + "al": 405, + "all": 664, + "all": 658, + "ally": 588, + "als": 796, + "am": 426, + "am": 817, + "ame": 552, + "ames": 976, + "amp": 800, + "an": 384, + "an": 425, + "ance": 751, + "and": 609, + "and": 780, + "ang": 816, + "ans": 844, + "ant": 837, + "ant": 753, + "any": 766, + "ap": 586, + "ar": 376, + "ar": 579, + "ard": 649, + "ards": 982, + "ary": 611, + "as": 416, + "as": 404, + "ase": 849, + "ased": 814, + "ason": 865, + "ass": 792, + "ast": 661, + "at": 372, + "at": 434, + "ate": 541, + "ated": 543, + "ater": 709, + "ates": 825, + "ath": 730, + "ating": 922, + "ation": 497, + "ational": 933, + "ations": 744, + "att": 903, + "aus": 858, + "av": 681, + "ay": 684, + "ay": 523, + "b": 67, + "b": 212, + "ber": 593, + "c": 68, + "c": 224, + "cc": 960, + "ce": 496, + "ces": 830, + "ch": 520, + "ch": 603, + "ct": 834, + "d": 69, + "d": 196, + "ded": 665, + "der": 690, + "ding": 633, + "ds": 530, + "duc": 671, + "e": 70, + "e": 195, + "ea": 471, + "ear": 596, + "ear": 669, + "ears": 906, + "eb": 852, + "ec": 418, + "ect": 838, + "ect": 964, + "ed": 563, + "ed": 362, + "ee": 941, + "een": 779, + "ef": 840, + "eg": 731, + "el": 407, + "el": 610, + "eld": 973, + "ell": 759, + "ell": 756, + "ely": 719, + "em": 455, + "ember": 777, + "ement": 959, + "emp": 975, + "en": 375, + "en": 427, + "ence": 685, + "ens": 880, + "ent": 478, + "ent": 468, + "ents": 674, + "ep": 545, + "er": 364, + "er": 374, + "eral": 793, + "ere": 481, + "ered": 748, + "eric": 921, + "erm": 861, + "ern": 887, + "ern": 977, + "ers": 598, + "ers": 486, + "ert": 986, + "ery": 805, + "es": 402, + "es": 388, + "ese": 794, + "ess": 678, + "ess": 693, + "est": 606, + "est": 584, + "et": 460, + "et": 594, + "etw": 824, + "etween": 886, + "ev": 493, + "evel": 980, + "ever": 855, + "ew": 687, + "ew": 612, + "ex": 938, + "ey": 713, + "f": 71, + "f": 209, + "fer": 911, + "ff": 587, + "for": 728, + "form": 901, + "fter": 634, + "g": 72, + "g": 214, + "ge": 592, + "h": 73, + "h": 203, + "i": 74, + "i": 205, + "ia": 605, + "ial": 672, + "ian": 638, + "ib": 726, + "ic": 395, + "ic": 510, + "ical": 625, + "ice": 782, + "ich": 561, + "ics": 996, + "id": 463, + "id": 613, + "ide": 739, + "ie": 974, + "ied": 812, + "ies": 516, + "if": 524, + "ig": 444, + "igh": 537, + "ight": 680, + "ik": 775, + "ike": 984, + "il": 406, + "il": 714, + "ile": 721, + "ill": 608, + "ill": 789, + "ily": 950, + "im": 469, + "im": 767, + "ime": 691, + "in": 358, + "in": 501, + "ine": 607, + "ing": 557, + "ing": 383, + "ings": 815, + "ion": 472, + "ion": 408, + "ional": 717, + "ions": 540, + "ip": 733, + "ip": 818, + "ir": 453, + "ir": 554, + "is": 393, + "is": 441, + "ish": 694, + "ish": 654, + "ished": 942, + "ision": 944, + "iss": 876, + "ist": 550, + "ist": 811, + "it": 378, + "it": 746, + "ite": 760, + "ited": 809, + "ition": 797, + "ity": 542, + "iv": 435, + "ive": 549, + "ived": 979, + "iz": 722, + "j": 75, + "j": 288, + "k": 76, + "k": 210, + "ked": 810, + "king": 924, + "ks": 692, + "l": 77, + "l": 201, + "la": 467, + "land": 743, + "ld": 559, + "le": 536, + "le": 465, + "les": 799, + "lud": 718, + "ly": 433, + "m": 78, + "m": 202, + "ment": 701, + "mp": 651, + "n": 79, + "n": 199, + "nd": 369, + "ned": 758, + "ning": 843, + "o": 80, + "o": 198, + "ob": 920, + "oc": 534, + "od": 575, + "og": 604, + "oh": 972, + "oin": 831, + "ol": 428, + "oll": 703, + "ollow": 928, + "olog": 932, + "om": 419, + "om": 883, + "ome": 663, + "on": 382, + "on": 390, + "ond": 872, + "one": 835, + "ong": 850, + "ong": 582, + "oo": 517, + "ood": 927, + "ook": 897, + "op": 531, + "op": 971, + "or": 377, + "or": 424, + "ore": 571, + "ors": 917, + "ort": 768, + "ort": 752, + "ory": 737, + "os": 447, + "ose": 881, + "ost": 646, + "ot": 600, + "ot": 879, + "ou": 392, + "oug": 659, + "ough": 798, + "ould": 640, + "oun": 553, + "ound": 961, + "our": 648, + "our": 772, + "ous": 712, + "out": 683, + "outh": 945, + "ov": 515, + "ow": 461, + "ow": 666, + "own": 657, + "oy": 952, + "p": 81, + "p": 217, + "per": 715, + "ph": 916, + "pp": 518, + "q": 82, + "q": 280, + "qu": 546, + "r": 83, + "r": 204, + "ra": 457, + "ran": 624, + "re": 367, + "ree": 765, + "ren": 790, + "res": 572, + "res": 747, + "ri": 487, + "rib": 804, + "ric": 745, + "rit": 589, + "ro": 385, + "rom": 498, + "rop": 826, + "roug": 803, + "ru": 951, + "ruc": 891, + "ry": 908, + "s": 84, + "s": 206, + "se": 741, + "sh": 795, + "so": 630, + "sp": 992, + "ss": 673, + "st": 519, + "st": 528, + "t": 85, + "t": 208, + "te": 954, + "ted": 489, + "ter": 535, + "ter": 505, + "th": 449, + "th": 488, + "ther": 576, + "ting": 676, + "tion": 570, + "tr": 619, + "ts": 436, + "tt": 720, + "tur": 953, + "ty": 821, + "u": 86, + "u": 229, + "ub": 591, + "ubl": 842, + "uc": 490, + "ud": 538, + "ue": 652, + "ug": 560, + "uil": 930, + "ul": 494, + "um": 532, + "um": 644, + "un": 448, + "und": 828, + "up": 833, + "up": 700, + "ur": 413, + "ure": 635, + "uring": 702, + "ury": 957, + "us": 438, + "us": 622, + "ust": 846, + "ut": 529, + "ut": 527, + "v": 87, + "v": 232, + "ve": 567, + "vi": 866, + "w": 88, + "w": 250, + "way": 970, + "wn": 999, + "x": 89, + "x": 269, + "y": 90, + "y": 211, + "yp": 993, + "z": 91, + "z": 228, + "|": 92, + "|": 304, + "}": 93, + "}": 336, + "~": 94, + "~": 343, + "¡": 95, + "¡": 220, + "¢": 96, + "¢": 306, + "£": 97, + "£": 323, + "¤": 98, + "¤": 292, + "¥": 99, + "¥": 339, + "¦": 100, + "¦": 303, + "§": 101, + "§": 275, + "¨": 102, + "¨": 282, + "©": 103, + "©": 259, + "ª": 104, + "ª": 286, + "«": 105, + "«": 266, + "¬": 106, + "¬": 319, + "®": 107, + "®": 329, + "¯": 108, + "¯": 287, + "°": 109, + "°": 298, + "±": 110, + "±": 200, + "²": 111, + "²": 284, + "³": 112, + "³": 272, + "´": 113, + "´": 307, + "µ": 114, + "µ": 261, + "¶": 115, + "¶": 301, + "·": 116, + "·": 326, + "¸": 117, + "¸": 257, + "¹": 118, + "¹": 241, + "º": 119, + "º": 260, + "»": 120, + "»": 247, + "¼": 121, + "¼": 305, + "½": 122, + "½": 294, + "¾": 123, + "¾": 316, + "¿": 124, + "¿": 271, + "Â": 125, + "Ã": 126, + "Ä": 127, + "Å": 128, + "Æ": 129, + "Ç": 130, + "È": 131, + "É": 132, + "Ê": 133, + "Ë": 134, + "Ì": 135, + "Í": 136, + "Î": 137, + "Ï": 138, + "Ð": 139, + "Ñ": 140, + "Ö": 141, + "×": 142, + "Ø": 143, + "Ù": 144, + "Ü": 145, + "à": 146, + "á": 147, + "â": 148, + "ã": 149, + "ä": 150, + "å": 151, + "æ": 152, + "ç": 153, + "è": 154, + "é": 155, + "ë": 156, + "ì": 157, + "ï": 158, + "Ċ": 159, + "Ċ": 349, + "Ġ": 160, + "Ġ\"": 401, + "Ġ'": 431, + "Ġ(": 475, + "Ġ)": 474, + "Ġ,": 360, + "Ġ.": 365, + "Ġ0": 847, + "Ġ1": 411, + "Ġ18": 769, + "Ġ19": 492, + "Ġ199": 893, + "Ġ1": 778, + "Ġ2": 462, + "Ġ20": 522, + "Ġ200": 620, + "Ġ201": 734, + "Ġ2": 813, + "Ġ3": 735, + "Ġ3": 888, + "Ġ4": 870, + "Ġ5": 907, + "Ġ5": 990, + "Ġ:": 637, + "Ġ;": 615, + "Ġ": 333, + "Ġ=": 399, + "Ġ@": 417, + "Ġ@,@": 755, + "Ġ@-@": 440, + "Ġ@.@": 696, + "ĠA": 409, + "ĠA": 807, + "ĠAl": 716, + "ĠAm": 829, + "ĠAmeric": 958, + "ĠAn": 784, + "ĠAr": 894, + "ĠB": 432, + "ĠC": 410, + "ĠCh": 581, + "ĠCom": 904, + "ĠD": 464, + "ĠE": 500, + "ĠEn": 878, + "ĠF": 470, + "ĠG": 482, + "ĠH": 445, + "ĠHe": 742, + "ĠI": 442, + "ĠI": 827, + "ĠIn": 704, + "ĠIn": 574, + "ĠIt": 774, + "ĠJ": 491, + "ĠK": 548, + "ĠL": 484, + "ĠM": 423, + "ĠMar": 776, + "ĠN": 483, + "ĠO": 504, + "ĠP": 450, + "ĠPar": 967, + "ĠR": 459, + "ĠS": 403, + "ĠSh": 750, + "ĠSt": 590, + "ĠT": 396, + "ĠTh": 414, + "ĠThe": 437, + "ĠThis": 997, + "ĠU": 585, + "ĠUn": 773, + "ĠV": 617, + "ĠW": 479, + "ĠWh": 853, + "ĠY": 757, + "Ġa": 356, + "Ġa": 394, + "Ġab": 653, + "Ġabout": 899, + "Ġac": 583, + "Ġacc": 874, + "Ġad": 656, + "Ġafter": 763, + "Ġag": 725, + "Ġal": 476, + "Ġalb": 991, + "Ġall": 839, + "Ġalso": 641, + "Ġan": 602, + "Ġan": 562, + "Ġand": 381, + "Ġapp": 711, + "Ġar": 507, + "Ġare": 601, + "Ġas": 454, + "Ġass": 947, + "Ġat": 514, + "Ġatt": 788, + "Ġb": 371, + "Ġbe": 499, + "Ġbe": 595, + "Ġbec": 706, + "Ġbeen": 686, + "Ġbeg": 915, + "Ġbetween": 914, + "Ġbo": 819, + "Ġbut": 623, + "Ġby": 473, + "Ġc": 368, + "Ġcent": 823, + "Ġch": 526, + "Ġchar": 822, + "Ġcl": 689, + "Ġcom": 509, + "Ġcomm": 707, + "Ġcomp": 616, + "Ġcon": 477, + "Ġcons": 841, + "Ġcont": 655, + "Ġcre": 931, + "Ġd": 387, + "Ġde": 627, + "Ġdec": 873, + "Ġdef": 965, + "Ġdes": 738, + "Ġdi": 892, + "Ġdis": 708, + "Ġduring": 864, + "Ġe": 421, + "Ġear": 854, + "Ġel": 869, + "Ġen": 662, + "Ġev": 682, + "Ġex": 539, + "Ġexp": 867, + "Ġf": 370, + "Ġfe": 845, + "Ġfil": 913, + "Ġfin": 786, + "Ġfir": 599, + "Ġfirst": 626, + "Ġfl": 877, + "Ġfor": 614, + "Ġfor": 458, + "Ġform": 963, + "Ġfrom": 503, + "Ġg": 430, + "Ġgame": 895, + "Ġgen": 985, + "Ġgro": 890, + "Ġh": 380, + "Ġha": 485, + "Ġhad": 566, + "Ġhas": 679, + "Ġhave": 667, + "Ġhe": 558, + "Ġher": 660, + "Ġhim": 896, + "Ġhis": 512, + "Ġi": 366, + "Ġimp": 909, + "Ġin": 429, + "Ġin": 389, + "Ġinc": 618, + "Ġinclud": 761, + "Ġind": 983, + "Ġint": 628, + "Ġinter": 832, + "Ġinto": 785, + "Ġis": 480, + "Ġit": 533, + "Ġits": 642, + "Ġj": 723, + "Ġk": 564, + "Ġkn": 857, + "Ġl": 398, + "Ġlar": 962, + "Ġlater": 936, + "Ġlea": 868, + "Ġm": 386, + "Ġmade": 949, + "Ġme": 968, + "Ġmore": 802, + "Ġmost": 910, + "Ġmov": 956, + "Ġmus": 966, + "Ġn": 415, + "Ġnew": 989, + "Ġno": 547, + "Ġnor": 978, + "Ġnot": 632, + "Ġnum": 926, + "Ġo": 359, + "Ġof": 373, + "Ġoff": 875, + "Ġon": 551, + "Ġon": 456, + "Ġone": 677, + "Ġonly": 871, + "Ġor": 699, + "Ġor": 645, + "Ġother": 787, + "Ġout": 925, + "Ġov": 729, + "Ġover": 856, + "Ġp": 379, + "Ġpar": 636, + "Ġper": 736, + "Ġpl": 698, + "Ġpla": 697, + "Ġplay": 808, + "Ġpos": 859, + "Ġpr": 889, + "Ġpre": 749, + "Ġpres": 912, + "Ġpro": 506, + "Ġproduc": 934, + "Ġqu": 955, + "Ġr": 521, + "Ġra": 863, + "Ġre": 400, + "Ġrec": 597, + "Ġrecor": 919, + "Ġreg": 943, + "Ġrel": 900, + "Ġrele": 946, + "Ġrem": 848, + "Ġrep": 762, + "Ġres": 650, + "Ġro": 629, + "Ġs": 361, + "Ġsa": 905, + "Ġsc": 732, + "Ġse": 569, + "Ġseason": 948, + "Ġsec": 781, + "Ġser": 740, + "Ġsev": 884, + "Ġsh": 513, + "Ġshe": 862, + "Ġsp": 578, + "Ġspec": 940, + "Ġst": 446, + "Ġstar": 939, + "Ġsu": 770, + "Ġsub": 969, + "Ġsuc": 764, + "Ġsuch": 981, + "Ġt": 354, + "Ġth": 355, + "Ġthan": 918, + "Ġthat": 452, + "Ġthe": 502, + "Ġthe": 357, + "Ġtheir": 621, + "Ġthem": 998, + "Ġthey": 727, + "Ġthis": 705, + "Ġthree": 902, + "Ġthroug": 923, + "Ġtime": 783, + "Ġto": 391, + "Ġtra": 836, + "Ġtw": 639, + "Ġtwo": 688, + "Ġun": 544, + "Ġup": 898, + "Ġus": 668, + "Ġused": 988, + "Ġv": 495, + "Ġw": 363, + "Ġwas": 422, + "Ġwere": 525, + "Ġwh": 443, + "Ġwhen": 851, + "Ġwhere": 995, + "Ġwhich": 573, + "Ġwhile": 935, + "Ġwho": 724, + "Ġwit": 451, + "Ġwith": 994, + "Ġwith": 466, + "Ġwor": 643, + "Ġwould": 801, + "Ġwrit": 937, + "Ġy": 580, + "Ġyear": 987, + "Ġâ": 556, + "ĠâĢ": 565, + "ĠâĢĵ": 631, + "ĠĊ": 412, + "Ģ": 161, + "Ģ": 223, + "ģ": 162, + "ģ": 273, + "Ĥ": 163, + "Ĥ": 262, + "ĥ": 164, + "ĥ": 337, + "Ħ": 165, + "Ħ": 278, + "ħ": 166, + "ħ": 281, + "Ĩ": 167, + "Ĩ": 308, + "ĩ": 168, + "ĩ": 225, + "Ī": 169, + "Ī": 221, + "ī": 170, + "ī": 244, + "Ĭ": 171, + "Ĭ": 315, + "ĭ": 172, + "ĭ": 321, + "Į": 173, + "Į": 324, + "į": 174, + "į": 302, + "İ": 175, + "İ": 249, + "ı": 176, + "ı": 332, + "IJ": 177, + "IJ": 295, + "ij": 178, + "ij": 313, + "Ĵ": 179, + "Ĵ": 328, + "ĵ": 180, + "ĵ": 312, + "Ķ": 181, + "Ķ": 256, + "ķ": 182, + "ķ": 314, + "ĸ": 183, + "ĸ": 277, + "Ĺ": 184, + "Ĺ": 322, + "ĺ": 185, + "ĺ": 285, + "Ļ": 186, + "Ļ": 267, + "ļ": 187, + "ļ": 290, + "Ľ": 188, + "Ľ": 311, + "ľ": 189, + "ľ": 299, + "Ŀ": 190, + "Ŀ": 291, + "ŀ": 191, + "ŀ": 293, + "Ł": 192, + "Ł": 335, + "ł": 193, + "ł": 252, + "Ń": 194, + "Ń": 297 +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/unet/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/unet/config.json new file mode 100644 index 0000000000000000000000000000000000000000..2df38f3145c1300d812b4a92a3cf328fee8b5485 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/unet/config.json @@ -0,0 +1,86 @@ +{ + "_class_name": "UNet2DConditionModel", + "_diffusers_version": "0.35.2", + "act_fn": "silu", + "addition_embed_type": null, + "addition_embed_type_num_heads": 64, + "addition_time_embed_dim": null, + "attention_head_dim": 8, + "attention_type": "default", + "block_out_channels": [ + 4, + 8 + ], + "center_input_sample": false, + "class_embed_type": null, + "class_embeddings_concat": false, + "conv_in_kernel": 3, + "conv_out_kernel": 3, + "cross_attention_dim": 32, + "cross_attention_norm": null, + "down_block_types": [ + "DownBlock2D", + "CrossAttnDownBlock2D" + ], + "downsample_padding": 1, + "dropout": 0.0, + "dual_cross_attention": false, + "encoder_hid_dim": null, + "encoder_hid_dim_type": null, + "flip_sin_to_cos": true, + "freq_shift": 0, + "in_channels": 4, + "layers_per_block": 1, + "mid_block_only_cross_attention": null, + "mid_block_scale_factor": 1, + "mid_block_type": "UNetMidBlock2DCrossAttn", + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "unet", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_sequence_length": 77, + "static_vae_scale_factor": 2, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_eps": 1e-05, + "norm_num_groups": 2, + "num_attention_heads": null, + "num_class_embeds": null, + "only_cross_attention": false, + "out_channels": 4, + "output_attentions": false, + "projection_class_embeddings_input_dim": null, + "resnet_out_scale_factor": 1.0, + "resnet_skip_time_act": false, + "resnet_time_scale_shift": "default", + "reverse_transformer_layers_per_block": null, + "sample_size": 32, + "time_cond_proj_dim": 32, + "time_embedding_act_fn": null, + "time_embedding_dim": null, + "time_embedding_type": "positional", + "timestep_post_act": null, + "transformer_layers_per_block": 1, + "transformers_version": null, + "up_block_types": [ + "CrossAttnUpBlock2D", + "UpBlock2D" + ], + "upcast_attention": false, + "use_linear_projection": false +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/unet/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/unet/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..bd7eafa68cc775b28c2de8e07ee5a11c5c4bfa1c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/unet/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:639ba609e8949f268113903d1d8924de79c42c3fa7cb0957e05b986049d6e01a +size 5037500 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_decoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_decoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..67f18bade80e4d02bba8ca5ad43ba1fcd6661010 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_decoder/config.json @@ -0,0 +1,62 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "latents_std", + "use_quant_conv", + "use_post_quant_conv", + "latents_mean", + "mid_block_add_attention", + "shift_factor" + ], + "act_fn": "silu", + "block_out_channels": [ + 4, + 8 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 1, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "vae-decoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 32, + "static_num_channels": 4, + "static_width": 32, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 2, + "out_channels": 3, + "output_attentions": false, + "sample_size": 32, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_decoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_decoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..d2512b6fb9b9ef36e4729a289934071ecdbeb777 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_decoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47cec67e0ed0ee65ab82e49e3b121ab4acda85561af117f3a6203b04cb324254 +size 1700339 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_encoder/config.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_encoder/config.json new file mode 100644 index 0000000000000000000000000000000000000000..0305f5579abb6da1d71c541c7f8fb2c193b64937 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_encoder/config.json @@ -0,0 +1,62 @@ +{ + "_class_name": "AutoencoderKL", + "_diffusers_version": "0.35.2", + "_use_default_values": [ + "latents_std", + "use_quant_conv", + "use_post_quant_conv", + "latents_mean", + "mid_block_add_attention", + "shift_factor" + ], + "act_fn": "silu", + "block_out_channels": [ + 4, + 8 + ], + "down_block_types": [ + "DownEncoderBlock2D", + "DownEncoderBlock2D" + ], + "force_upcast": true, + "in_channels": 3, + "latent_channels": 4, + "latents_mean": null, + "latents_std": null, + "layers_per_block": 1, + "mid_block_add_attention": true, + "neuron": { + "auto_cast": "matmul", + "auto_cast_type": "bf16", + "compiler_type": "neuronx-cc", + "compiler_version": "2.26.6360.0+6f180f47", + "dynamic_batch_size": false, + "float_dtype": "fp32", + "inline_weights_to_neff": true, + "instance_type": "inf2", + "int_dtype": "int64", + "model_type": "vae-encoder", + "optlevel": "2", + "output_attentions": false, + "output_hidden_states": false, + "static_batch_size": 1, + "static_height": 64, + "static_num_channels": 3, + "static_width": 64, + "task": "semantic-segmentation", + "tensor_parallel_size": 1 + }, + "norm_num_groups": 2, + "out_channels": 3, + "output_attentions": false, + "sample_size": 32, + "scaling_factor": 0.18215, + "shift_factor": null, + "transformers_version": null, + "up_block_types": [ + "UpDecoderBlock2D", + "UpDecoderBlock2D" + ], + "use_post_quant_conv": true, + "use_quant_conv": true +} diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_encoder/model.neuron b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_encoder/model.neuron new file mode 100644 index 0000000000000000000000000000000000000000..711d64aa8a48586035950cae359f90fcc26ac806 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c6310bffbfbf29e5d927/vae_encoder/model.neuron @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ee8c39567e06350b847037c9f1ad40cf0bc7ede108cb659be12064bb0edaee +size 1328819 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..9e1ab7bd799e336530d9aa750d1e5eafb345f299 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb467306c906c5c2d4902f9a6bf9e8f58d81c53cbb93f5a47fe4f6344b312941 +size 2234340 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..afe5ebecdfa096a9570cfef2e680c547c690f135 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_c667425442470fb41cc2+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19fe1d7b661cc27561c74fa7482ac0c44fca07ae3c86c8f9e2fc16841876528d +size 2632704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..99dcce86d39249410d5b045a063913f11927efec --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:344371a33e82cc0e79c8b6988ef5af25c9d324713a46233333a30b8b98a38c84 +size 2231014 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..08f4cfb104ca9c35468b6bce3bbd825d526a04e2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_cceaa2d0540a8dc32a5a+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:157b4c74a03870dcf346faf417ff9f6da25c38b50b9083b0a39a46bcf42eb0c8 +size 2632704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3ed7cdba5ef44a455bcc300e2c72fa63043aa03b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020b3226eeb42ce0aadfedf83c76542ad97fb7a8f5882e2be787a2649be5d30b +size 1281258 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3814ac4a9f79413917e0307bbf6a5e3503d86ff5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dccda32ed026f04a09f8+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96bf1a392ca04ea1f24b0970acebf4ab3da4d1e7e5407864a6c44f6c62b23507 +size 3267584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5d5f55d8a61ad692c8a9905e7ac124cc76a636ad --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:453d181e4e02fea281f7d7e96354b5790dcd122da1af0c0f9cd671d9d2dea6e7 +size 246664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..044a693b854d7f078629a15087c865cdcd44453b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd3c57cb3f607b586f3b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a245efb43e0bc49d3d9e1e20e286ece9c227cbe1f5e9cae281191edd1c14c5 +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e62697edb55f6c67117af07d6b71a0d1d0bfcfaf --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0c42b26fdf4ec4f04773d4f518349bc180a07c04b3733382897251e6ab97cc +size 2162155 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fe0966fa459ca0a3265b594120360c464d6a1530 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c2359b7cab2adde2c2b6397c1266aeb5f4c7bdf66a70f80d3b98a14e1c55cd60 +size 1649664 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a2ab49a4561e898fcfcb7dcad467e1a253a411cb --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dd6d9cd7ecff6fd57d40+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91660292e803438454ebc15beadd45098468e899f783c8d552fb91970f9522af +size 1805855 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..8708f500fa9dbe3756e648878839741ef1621ff5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2a4f4532e1d40bad57643ecbc43f3f9e73a6411a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a3d6745a7b415bb5545db253b16d32fac4aabc6b53f7687081e1ee73eaadf99 +size 1703829 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..609a1200d7197e9a337ff28192b63728af85e48c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_dedc330f2ecabe0f6b62+97496b47/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15b7401583e628a7b47c60029da3a2aeff83614af825cce38080f45faba6d4ae +size 26420224 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bc8ac477df36cb96322c190748055a3557dd0f46 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00fb9406bd2cdfef4eac1be94b62473abab868ed548085d5a79cd64b3e063318 +size 269001 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d7547bbd31ff750e8e73a0e905530dfcd8af696e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:378748ea944cd50b5741529a83703bc140ef42cf971a64ba5ea92c801b2e06ab +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..a6f0ef17f922c259a11f3c64d81e69d702194e1d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d20c9f7f58e19f6fd+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40a131d1d80f04b6b1e1870ac33de53df8a4acad2c610a105312e02e6f7e2268 +size 234517 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b6c20b995ba5a1d8db7f11da26b7b5567c9bd05c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad0c6944a2643e4157a2c4a94659a84fe9f6e76ac9c30ac67148f842e8ee8cf1 +size 1440206 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..55d5627ec8a9e29dd273128a183ba4d2f340691a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15d6fbe10adcb6dba5be99816fd79a15c815398d4c134c65ad3ecf8b9cbbe6e0 +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..30196375f8b523e229cf29406f4594c7135a6464 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e01d7b8d87f66fb4c5c4+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bd94a17f7434507428cbb4a5288051b07fd38e2e974d0e255d29010c334170e +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..33b10fa1459c4f81e590a4f3ab4ff2a1f29ea7ec --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73d697db7bc8de05bbbbc46ae8e768c2eb32c4f948c7dc9833912ec98145c3e9 +size 3086461 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..96b9d7ab46363015bfa2972631c6ccb3b392390d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47fbfedb979db908ac5f13692fd3fe5dacd87fcc7c321dfec8f87bf905c9b1d8 +size 5315584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ce3d82f46c9eea268052e78a2047f8d30924a29b --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e0e784ebf4b73fdc8a51+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d494dd4d6cb3690e4591f7799ddc9ab27150dc0e99398fe41e192f189efa35f +size 5482108 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c5408e82de9ffc6a691997e9ac38d9e72111fc45 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae4f7766dfa6d1ef493c782841c199569d912b36c41f20fcbe6d913d2c2a182e +size 1284078 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3abca73e0a863f3aabc9f360243e863ebefc5a70 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e585b7ba3d40121c96d4+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c22d1fa6bf378311574a7d4ae4a2c3a72253f21de2dfbfe2a70589c2ed5ed2a7 +size 3267584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..de2aff593542a74404a3ebf4cd34571cd3e08621 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d128ddd84a3e8cb0189b2b236d1477c96d56ae75d31a65aff79902e22a7cf8c3 +size 1796116 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1950c7b3a2bd5e3862f663c2214842039e59014a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e6f172aca340ebc38f62+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b74692a0a3390e7a6e36717f7dc7a47c57574ab3319a2119cae62fa45814e66f +size 1731584 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..95196af4946ea37f863ed8de3258d824cec9fea9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a116a020066fc50e307b10bdde4e9ffb0d1a2e9c7191237e62497a15e4c90ae +size 221634 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..bb536bc29b4302532b81db5c522f962eb9980c03 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_e84ea5bc122d4d45ea24+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78549d0495f698a88a0f60c13d9a230366b36e1c38567b48fde708b1b0af5ec9 +size 267264 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e9c3f17cb0d21ea1aba13c97f429f500712ddca5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0807b4534875c68fb67242583f28212d275cfb5aec9d85dda1f498d5f263620b +size 2239180 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..96bb92231e14e20f626ef8f6e74d5f989adb67ef --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef28fda949fc4d59f2ca6537f2fb7c14636ec73fc892fb43acb9f7c71a01e9d3 +size 1700864 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..dc666157ee20062288bea961b315d35aba05302e --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ea1100f623c4d5b3dd18+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a91be0320bb7496d18ccc6e2f5abb50a0586099ad6f0f3e5181995e59f54dcb +size 1857170 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..61ef6ba19a6792c3166c5152ba1830698a2390a2 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc4549b37753450fc01911b4e1dfa75122fd35d731b169a0762717c9f0c5048b +size 3325563 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..892cf999332d7db58939cf851dbf123b4c921111 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_eda9e5170145f93ff69b+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975a2757c9cbf690b53f9929a0b6be3170d3513725946778fe87a85386a17c4b +size 5080064 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..ac48f16f24a44dd41a06a92712e79367ca139197 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4989dd4b58a9783dab251e345d4fe1b41e3d48c3b55247f03bc14dac806eccb +size 1393605 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1ab25e8f8179baabb9eebc46e5f17303438905ab --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a7f5d8d4bc3eafcbd07774d54bbd1668a61897c5f9248a16bef32782c09e09d +size 1946624 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..228f77870769633a86d02a7b8d778ba288ee5d55 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ee7d4038286fa40eb024+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b5cf1519ab7e72245c4b4043f4a7fdd220de1fd63f01c92e95dea8164720418 +size 2039537 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..53716fd5f3f619b673e294ab2b617799624f5682 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e252918450884c004fe2164e046d901b30ab14e0b321dea8a69c3991061bf218 +size 1436432 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3e23cc4276f01a2455f4bb3468dacec07da9498a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7bdd221f815c567c9c3c4039706974b83d0987612ed2208e25cf5b94914c48f +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..647fe86df645292d1cf7cac9355caf306904d757 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_ef274caa64bc859f5c5c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ba931a2848b10dcb36ce6acb99ce7d8317edd5713a2a8d7233b87874e7c3f97 +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..073152b3a2ef237211afd52e67e995962b0fa4f5 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c49bf0c58c25507a7cf81d8c6e270987d93e706aa17590644569ec6cdfa8eb8 +size 3524024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d489e48e9451b785600d9d71b796426f380c2eb3 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b905d31fbffa7cc6dda0f2b0353df6daee8a3fb728e2b65020295b4613c5e3 +size 6657024 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..bf2e0111a3f723c488b900df04523890c7d39cc7 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_efd6f44c6d257085505e+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c05f227935208f9ede55803793107fec92c29783d03be9f4a2c6d962a9e48bf1 +size 6887798 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..043d6e4074631e832c744d21e67006afb148e60d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..fb0281c480004f635495876b10e009898adefcc1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0765627f4f9eec199a74db4baf07d8b17ec2fe5f6c3cd12129c8063895168a63 +size 3229243 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..902c466098d981c3c4b737eb624f504a497070ba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f27c5b2a1477f1506e0c+12dd9119/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a99680d692f6b08501006bebae2152a967b5f9252222343680f9dfbe75648bc8 +size 19303424 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..50d949def2ddfcf70e1fc7b0915bf68c974e28f9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b024a86abbbb08a23506216820912402ebc18b09a457a5f30bc7eadb0c9ad378 +size 241800 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..0e1b65b4f679394fe26291f5505a7e206d708333 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a5c19c3c44dc5f0a7bada64a098b226666b06dfb84cd66e57406e899064b5ae +size 226304 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7ae60f7b91448bf8adfbc73703c2a70d45ab8a3f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f3069378727ea3b17875+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e80adcbd149a6cc88cdf46dada3180b46a9885cadb7a6c4645b99e2ede8ff3 +size 234517 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..c27e6c39a7a4c3b736e614d7725e8bfa29486eb1 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/speculation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5902ae6960596566a5e4df05a31e7c0fa2b4790d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9e98b223113ebe071c2c8d74b1b66d1ab79ac18c699ec69b869b95462251284 +size 1559140 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..4e9dd31214eaa9e6962f32083af029c429bc7683 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f56602829db90683aac8+0788fa03/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4de3dcf7b5774e6bd371bc253c48cd2eda21fbce680be38d55dc604a4ff21a82 +size 3656704 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e822c9c9ac962b7cbb1d570371be109c62a1e859 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a80d4dd9c998b010600028af0ffaddc8e1b97c8f1db292a20860997a8423f36 +size 3045236 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1889f2d68a7dcaf85e8fa7a6ad8061e40a4417f6 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98ec34f5b84dfdcf132199393181e04951f9ca4f6e28a7d0568b16f1e3534816 +size 5305344 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..8ccc581dccdaccb97059e773379e1d0cf4f752ab --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f685396b88bb9384006c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b47105f7bdca36041f88decdd49b518f1950b798403322fce51a7c5daf8b1f +size 5471868 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..90a6e8b6e09dccd14222a4560c8c081b2178f8c0 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca7a84cf2345311fd8b46292f5a7bda1309d3e9d6ec703a2fc149f0fa0b8dde2 +size 1438478 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d0b4c0ee34acd363909d1aec80d13c8cd7414e8c --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2dcc5827c06dc522395cb70466404e9219cd751f1cdc1ac9dc14806b9d1b07db +size 2253824 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..44d1006b5f96004170e56e8d10af34877e34520f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_f7c7d17145ae2991812c+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c3265be9299d2e68d1e5990d2ed1682a58a0b24cfcc74249d00ac538ced1cd +size 2328023 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..1758ee2b48d0bf7ae7156a561c187fd1efc9719a --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:444a987972e318a88ad030c7bd2b3cad27e8254e1d47f91b9ad059d86880a399 +size 3067821 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..58dc131a281f14863087826c38a8cdb82d16a546 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a02b32c5962416dc6df534b313a1279d3beca47b5c3d87ba050e17180804b58 +size 5305344 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..55d16d55f55aa89baafe939f9ce5138eb7283230 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fb55b8eb238996c22393+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64cf448dfa239652a5f69c707641d72a46d1442c9883c5515520fbb5dda27271 +size 5471868 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..46db31d3c333a208f1a44ff933642390ee2b728d --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..27adb4c0539151876bd1516cf4401a96c158a707 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2174fa839ce5e178289e91216b4d433a8bfabbaa8816752ec6d9b3a45de2e4bd +size 209487 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..284c715d42d839d6131216915444ef78a2a860d8 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cd0e4841d782d22bd918e7c6a301ac555ed6cb87ce1663845cce3ce8fab946d +size 297984 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..1ef82fdbafd16dbbe9767552f8a06b4cb5ba07c9 --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fc09d37f2c192c8b245b+84337dd9/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd1b71919afbf955a2c39dc4adfc803c920a48d2c0cff43efcc2e41ff9d1fad +size 306129 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/compile_flags.json b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..3ceda35df13d9f1ba719ce3eda3655a42e44fdba --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"] \ No newline at end of file diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.done b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.hlo_module.pb b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0c26554d62612c83d12072278729131479bbb0df --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97636f1e59d1aeb06ad5974096783b13b4d64e771f8dec6f7a6234a31061321a +size 1739721 diff --git a/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.neff b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..40d59bbcde40cba1262ffb2d777823d9375af98f --- /dev/null +++ b/neuronxcc-2.26.6360.0+6f180f47/MODULE_fe693526a669de0d2c0c+519f203d/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f79a1159dd62507153e863479261cf7260b87f53d28e781c2bc2597d61c16aff +size 1731584