Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +169 -0
- neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/032a200921861dc047e7.json +83 -0
- neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/39e136137a684fed0cfe.json +83 -0
- neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/f0f57ac10fe3b261d3b4.json +83 -0
- neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/d915dcdd91e8e2f04ff262f036618c2a933bae11f6700cdeb4bb8d5c1aca1be0/c673eb5b8790b0c8fdef.json +87 -0
- neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/qwen2/Qwen/Qwen2.5-1.5B/c673eb5b8790b0c8fdef.json +87 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/model.neff +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/wrapped_neff.hlo +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/model.neff +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/wrapped_neff.hlo +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/model.neff +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/wrapped_neff.hlo +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/model.neff +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/wrapped_neff.hlo +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/model.neff +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/wrapped_neff.hlo +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/model.neff +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/wrapped_neff.hlo +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/model.neff +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/model.neff +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/wrapped_neff.hlo +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/compile_flags.json +1 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/model.done +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/model.hlo_module.pb +3 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/model.neff +0 -0
- neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/wrapped_neff.hlo +0 -0
.gitattributes
CHANGED
|
@@ -7581,3 +7581,172 @@ neuronxcc-2.23.6484.0+3b612583/MODULE_c4e977bb7926de11645f+781055f7/model.neff f
|
|
| 7581 |
neuronxcc-2.23.6484.0+3b612583/MODULE_dc4deb74509065822576+dae43e99/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7582 |
neuronxcc-2.23.6484.0+3b612583/MODULE_dc4deb74509065822576+dae43e99/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7583 |
neuronxcc-2.23.6484.0+3b612583/MODULE_6405f23847f4597dd89a+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7581 |
neuronxcc-2.23.6484.0+3b612583/MODULE_dc4deb74509065822576+dae43e99/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7582 |
neuronxcc-2.23.6484.0+3b612583/MODULE_dc4deb74509065822576+dae43e99/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7583 |
neuronxcc-2.23.6484.0+3b612583/MODULE_6405f23847f4597dd89a+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7584 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7585 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7586 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7587 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7588 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7589 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7590 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7591 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7592 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7593 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7594 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7595 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7596 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7597 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1d96448d859bd6dbf749+5998014f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7598 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_1d96448d859bd6dbf749+5998014f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7599 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_238f46260fad16e0a2d5+aaf1acf8/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7600 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_238f46260fad16e0a2d5+aaf1acf8/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7601 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2724a0e8973f8924b2ba+d9d91b6e/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7602 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2724a0e8973f8924b2ba+d9d91b6e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7603 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2998f698865cc9066bb7+63384570/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7604 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2998f698865cc9066bb7+63384570/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7605 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2cb1a0fe976c460888b1+9053b695/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7606 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2cb1a0fe976c460888b1+9053b695/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7607 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2d0be984e9dff501cd13+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7608 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2e619e7c3d245ea2a9d5+830f2030/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7609 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_2e619e7c3d245ea2a9d5+830f2030/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7610 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_32cbb2e0924d5c7ed560+0a85e4f6/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7611 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_32cbb2e0924d5c7ed560+0a85e4f6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7612 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_336e90ddc9c225c9be51+dac70ec8/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7613 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_336e90ddc9c225c9be51+dac70ec8/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7614 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_3524943ac9de679fa185+dae43e99/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7615 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_3524943ac9de679fa185+dae43e99/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7616 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_35e403ca9337fa777d3b+50d95d3e/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7617 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_35e403ca9337fa777d3b+50d95d3e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7618 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_381ff733441ab9635f88+59da5d62/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7619 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_381ff733441ab9635f88+59da5d62/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7620 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_3969c5387e4b85c2a202+510f2408/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7621 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_3969c5387e4b85c2a202+510f2408/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7622 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_39e3e9ff67dd9abf6773+3f6758e9/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7623 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_39e3e9ff67dd9abf6773+3f6758e9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7624 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_3ef14e9f6345f59b0bcf+00fdbb21/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7625 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_3ef14e9f6345f59b0bcf+00fdbb21/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7626 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_40ee19b5a4f1df873479+1682a314/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7627 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_40ee19b5a4f1df873479+1682a314/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7628 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_45ad47bdbe66f0b1aaf8+888e3c60/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7629 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_45ad47bdbe66f0b1aaf8+888e3c60/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7630 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_48b0bf05e6bf18617486+dae43e99/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7631 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_48b0bf05e6bf18617486+dae43e99/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7632 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_50d7f41399c441455dd2+f0a766fc/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7633 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_50d7f41399c441455dd2+f0a766fc/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7634 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_54ed98e82074922fa57c+47d62118/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7635 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_54ed98e82074922fa57c+47d62118/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7636 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_577fbaa002851141ad8a+9daec842/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7637 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_577fbaa002851141ad8a+9daec842/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7638 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_5b0bdace453a7af87347+3869be05/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7639 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_5b0bdace453a7af87347+3869be05/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7640 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_5d74a28c56aa82d3f75a+b71f9755/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7641 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_5d74a28c56aa82d3f75a+b71f9755/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7642 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_5da80bcb09c227c50ca7+fd379df6/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7643 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_5f6a35b7a27919d6aaee+6c83b616/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7644 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_5f6a35b7a27919d6aaee+6c83b616/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7645 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_62388ee4ec0d80289271+6ab871d9/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7646 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_62388ee4ec0d80289271+6ab871d9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7647 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_62d541fcb35a5e38bd0a+89e835dd/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7648 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_62d541fcb35a5e38bd0a+89e835dd/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7649 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_631952062d21d2e63b4b+4defe15f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7650 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_631952062d21d2e63b4b+4defe15f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7651 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_639907989212e6548606+bd7b152d/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7652 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_639907989212e6548606+bd7b152d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7653 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_6c795c50dcbf7b7b0a03+3da6fb2b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7654 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_6c795c50dcbf7b7b0a03+3da6fb2b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7655 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_6d77ccf824d24ea825e0+133e71b3/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7656 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_6d77ccf824d24ea825e0+133e71b3/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7657 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_736971a1712e7a456df4+d3b950ac/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7658 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_736971a1712e7a456df4+d3b950ac/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7659 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_7b2ee5102ce9c77ede72+3cd3e530/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7660 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_7b2ee5102ce9c77ede72+3cd3e530/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7661 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_7dcc5824b614d8561b49+cb4ac5d3/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7662 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_7dcc5824b614d8561b49+cb4ac5d3/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7663 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_7e1d8bfb798fdd0d1ae6+f5385b37/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7664 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_7e1d8bfb798fdd0d1ae6+f5385b37/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7665 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_801633b6eb7c2f72dffe+7d99dcc2/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7666 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_801633b6eb7c2f72dffe+7d99dcc2/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7667 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_8417c8bd11020d8d1044+6ab534e6/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7668 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_8417c8bd11020d8d1044+6ab534e6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7669 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_84c0e29044e88f3be9c6+d61fca59/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7670 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_84c0e29044e88f3be9c6+d61fca59/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7671 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_8c5bc74c3167749716d7+e000d124/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7672 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_8c5bc74c3167749716d7+e000d124/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7673 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_8fd69ab09c8bccbc409c+76c4f39e/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7674 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_8fd69ab09c8bccbc409c+76c4f39e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7675 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_9beaf48e54021f5647fd+ce2964b7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7676 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_9beaf48e54021f5647fd+ce2964b7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7677 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_9c9ebdda66998f70ace4+99e90774/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7678 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_9c9ebdda66998f70ace4+99e90774/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7679 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a1716e3644f621c505a0+dae43e99/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7680 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a1716e3644f621c505a0+dae43e99/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7681 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a2092762e12a1458e9a9+8c7c8cab/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7682 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a2092762e12a1458e9a9+8c7c8cab/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7683 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a267b7460b15490d3807+bc197b23/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7684 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a267b7460b15490d3807+bc197b23/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7685 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a4b48821d295c7f87f6e+0657c3e0/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7686 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a4b48821d295c7f87f6e+0657c3e0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7687 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a5accbc0d1e5f97dcc94+4d31f90a/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7688 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_a5accbc0d1e5f97dcc94+4d31f90a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7689 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_aff5c5236076329040ce+693f32f3/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7690 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_aff5c5236076329040ce+693f32f3/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7691 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_b5202f0be0998a8b196a+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7692 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_b92b7bd8973e230a61ce+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7693 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_bcade6f0d9cafa4b2d77+62d8a9a0/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7694 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_bcade6f0d9cafa4b2d77+62d8a9a0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7695 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_bfc293829d465427e339+e1f2c691/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7696 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_bfc293829d465427e339+e1f2c691/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7697 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c076dd4f3a023cb4c14d+6ce2ae21/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7698 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c076dd4f3a023cb4c14d+6ce2ae21/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7699 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c0bc3d0a98eaff82078c+fe9ef6ca/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7700 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c0bc3d0a98eaff82078c+fe9ef6ca/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7701 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c1d5f852a5d2ad71b040+d2242ae9/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7702 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c1d5f852a5d2ad71b040+d2242ae9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7703 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c44657ef6abd93bbf6f0+fca303d4/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7704 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c44657ef6abd93bbf6f0+fca303d4/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7705 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c88fe926847ceb3007de+8b190d35/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7706 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c88fe926847ceb3007de+8b190d35/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7707 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c9bc1e38fefc277e20c9+80f7ecc2/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7708 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_c9bc1e38fefc277e20c9+80f7ecc2/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7709 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ccacab4f3bcc00061dce+f5a1a20a/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7710 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ccacab4f3bcc00061dce+f5a1a20a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7711 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ceea45e12f877a7a6d32+a3c4b755/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7712 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ceea45e12f877a7a6d32+a3c4b755/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7713 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_d154e4430055fe592459+a755fc87/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7714 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_d154e4430055fe592459+a755fc87/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7715 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_d3203b6d5cc827d435a3+7d1d483a/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7716 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_d3203b6d5cc827d435a3+7d1d483a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7717 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_d3e1ca818568e8df7110+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7718 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_d5b1ab5c4df975c440ed+739dcb83/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7719 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_d5b1ab5c4df975c440ed+739dcb83/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7720 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_dc347363bd76c60d4755+dc79dd3e/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7721 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_dc347363bd76c60d4755+dc79dd3e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7722 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_e2fab62b1b0c4e83b659+2b38c450/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7723 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_e2fab62b1b0c4e83b659+2b38c450/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7724 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_e63b9a3ff2ce5b6ce631+99b0c65b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7725 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_e63b9a3ff2ce5b6ce631+99b0c65b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7726 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ea7e778f43bc3a28131a+81f44b8d/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7727 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ea7e778f43bc3a28131a+81f44b8d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7728 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_eaf6423c17af6e2baf45+2dc7f812/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7729 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_eaf6423c17af6e2baf45+2dc7f812/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7730 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_eb1f4018beccc6fcfecf+03899f9a/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7731 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_eb1f4018beccc6fcfecf+03899f9a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7732 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ecbe50386577f0587c97+781055f7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7733 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ee2a61caab811bc4a92b+ccfe2ded/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7734 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ee2a61caab811bc4a92b+ccfe2ded/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7735 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ef7187a7707004d2b24d+ef5ba5e7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7736 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_ef7187a7707004d2b24d+ef5ba5e7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7737 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f042b11116c61e303b5c+879c9cfc/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7738 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f042b11116c61e303b5c+879c9cfc/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7739 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f2b691e69141b108e4a7+f136d8ea/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7740 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f2b691e69141b108e4a7+f136d8ea/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7741 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f47578def5bc42598a43+c10db20d/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7742 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f47578def5bc42598a43+c10db20d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7743 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f6e53862178c9ee8c279+6067088b/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7744 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f6e53862178c9ee8c279+6067088b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7745 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f75532b27d54ec2ee87d+74407cb5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7746 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f75532b27d54ec2ee87d+74407cb5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7747 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f890982a927bfd05e307+4f55ebfa/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7748 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f890982a927bfd05e307+4f55ebfa/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7749 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f9f9eb6ad280e653854e+5bf3ac57/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7750 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_f9f9eb6ad280e653854e+5bf3ac57/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 7751 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_fb7fa50fef7f1cb3a8dd+35b212ac/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 7752 |
+
neuronxcc-2.23.6484.0+3b612583/MODULE_fb7fa50fef7f1cb3a8dd+35b212ac/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/032a200921861dc047e7.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 896,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4864,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention"
|
| 39 |
+
],
|
| 40 |
+
"max_position_embeddings": 32768,
|
| 41 |
+
"max_window_layers": 24,
|
| 42 |
+
"model_type": "qwen2",
|
| 43 |
+
"neuron": {
|
| 44 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 45 |
+
"batch_size": 4,
|
| 46 |
+
"capacity_factor": null,
|
| 47 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 48 |
+
"checkpoint_revision": null,
|
| 49 |
+
"continuous_batching": true,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"max_batch_size": 4,
|
| 55 |
+
"max_context_length": 1024,
|
| 56 |
+
"max_topk": 256,
|
| 57 |
+
"n_active_tokens": 1024,
|
| 58 |
+
"neuronxcc_version": "2.23.6484.0+3b612583",
|
| 59 |
+
"on_device_sampling": true,
|
| 60 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 61 |
+
"output_logits": false,
|
| 62 |
+
"pp_degree": 1,
|
| 63 |
+
"prefill_chunk_size": 0,
|
| 64 |
+
"sequence_length": 1024,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": "trn1",
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/39e136137a684fed0cfe.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 896,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4864,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention"
|
| 39 |
+
],
|
| 40 |
+
"max_position_embeddings": 32768,
|
| 41 |
+
"max_window_layers": 24,
|
| 42 |
+
"model_type": "qwen2",
|
| 43 |
+
"neuron": {
|
| 44 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 45 |
+
"batch_size": 1,
|
| 46 |
+
"capacity_factor": null,
|
| 47 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 48 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 49 |
+
"continuous_batching": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 1,
|
| 54 |
+
"max_batch_size": 1,
|
| 55 |
+
"max_context_length": 128,
|
| 56 |
+
"max_topk": 256,
|
| 57 |
+
"n_active_tokens": 128,
|
| 58 |
+
"neuronxcc_version": "2.23.6484.0+3b612583",
|
| 59 |
+
"on_device_sampling": false,
|
| 60 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 61 |
+
"output_logits": false,
|
| 62 |
+
"pp_degree": 1,
|
| 63 |
+
"prefill_chunk_size": 0,
|
| 64 |
+
"sequence_length": 128,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": "trn1",
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"tp_degree": 1
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/f0f57ac10fe3b261d3b4.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 896,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4864,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention"
|
| 39 |
+
],
|
| 40 |
+
"max_position_embeddings": 32768,
|
| 41 |
+
"max_window_layers": 24,
|
| 42 |
+
"model_type": "qwen2",
|
| 43 |
+
"neuron": {
|
| 44 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 45 |
+
"batch_size": 1,
|
| 46 |
+
"capacity_factor": null,
|
| 47 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 48 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 49 |
+
"continuous_batching": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"max_batch_size": 1,
|
| 55 |
+
"max_context_length": 128,
|
| 56 |
+
"max_topk": 256,
|
| 57 |
+
"n_active_tokens": 128,
|
| 58 |
+
"neuronxcc_version": "2.23.6484.0+3b612583",
|
| 59 |
+
"on_device_sampling": false,
|
| 60 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 61 |
+
"output_logits": false,
|
| 62 |
+
"pp_degree": 1,
|
| 63 |
+
"prefill_chunk_size": 0,
|
| 64 |
+
"sequence_length": 128,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": "trn1",
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/d915dcdd91e8e2f04ff262f036618c2a933bae11f6700cdeb4bb8d5c1aca1be0/c673eb5b8790b0c8fdef.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-1.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1536,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8960,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 131072,
|
| 45 |
+
"max_window_layers": 28,
|
| 46 |
+
"model_type": "qwen2",
|
| 47 |
+
"neuron": {
|
| 48 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 49 |
+
"batch_size": 1,
|
| 50 |
+
"capacity_factor": null,
|
| 51 |
+
"checkpoint_id": "Qwen/Qwen2.5-1.5B",
|
| 52 |
+
"checkpoint_revision": "8faed761d45a263340a0528343f099c05c9a4323",
|
| 53 |
+
"continuous_batching": false,
|
| 54 |
+
"ep_degree": 1,
|
| 55 |
+
"fused_qkv": false,
|
| 56 |
+
"glu_mlp": true,
|
| 57 |
+
"local_ranks_size": 2,
|
| 58 |
+
"max_batch_size": 1,
|
| 59 |
+
"max_context_length": 8192,
|
| 60 |
+
"max_topk": 256,
|
| 61 |
+
"n_active_tokens": 8192,
|
| 62 |
+
"neuronxcc_version": "2.23.6484.0+3b612583",
|
| 63 |
+
"on_device_sampling": true,
|
| 64 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 65 |
+
"output_logits": false,
|
| 66 |
+
"pp_degree": 1,
|
| 67 |
+
"prefill_chunk_size": 1024,
|
| 68 |
+
"sequence_length": 8192,
|
| 69 |
+
"speculation_length": 0,
|
| 70 |
+
"start_rank_id": 0,
|
| 71 |
+
"target": "trn1",
|
| 72 |
+
"torch_dtype": "bfloat16",
|
| 73 |
+
"tp_degree": 2
|
| 74 |
+
},
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_hidden_layers": 28,
|
| 77 |
+
"num_key_value_heads": 2,
|
| 78 |
+
"rms_norm_eps": 1e-06,
|
| 79 |
+
"rope_scaling": null,
|
| 80 |
+
"rope_theta": 1000000.0,
|
| 81 |
+
"sliding_window": null,
|
| 82 |
+
"tie_word_embeddings": true,
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_mrope": false,
|
| 85 |
+
"use_sliding_window": false,
|
| 86 |
+
"vocab_size": 151936
|
| 87 |
+
}
|
neuronxcc-2.23.6484.0+3b612583/0_REGISTRY/0.4.6.dev3/qwen2/Qwen/Qwen2.5-1.5B/c673eb5b8790b0c8fdef.json
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-1.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1536,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 8960,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention"
|
| 43 |
+
],
|
| 44 |
+
"max_position_embeddings": 131072,
|
| 45 |
+
"max_window_layers": 28,
|
| 46 |
+
"model_type": "qwen2",
|
| 47 |
+
"neuron": {
|
| 48 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 49 |
+
"batch_size": 1,
|
| 50 |
+
"capacity_factor": null,
|
| 51 |
+
"checkpoint_id": "Qwen/Qwen2.5-1.5B",
|
| 52 |
+
"checkpoint_revision": "8faed761d45a263340a0528343f099c05c9a4323",
|
| 53 |
+
"continuous_batching": false,
|
| 54 |
+
"ep_degree": 1,
|
| 55 |
+
"fused_qkv": false,
|
| 56 |
+
"glu_mlp": true,
|
| 57 |
+
"local_ranks_size": 2,
|
| 58 |
+
"max_batch_size": 1,
|
| 59 |
+
"max_context_length": 8192,
|
| 60 |
+
"max_topk": 256,
|
| 61 |
+
"n_active_tokens": 8192,
|
| 62 |
+
"neuronxcc_version": "2.23.6484.0+3b612583",
|
| 63 |
+
"on_device_sampling": true,
|
| 64 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 65 |
+
"output_logits": false,
|
| 66 |
+
"pp_degree": 1,
|
| 67 |
+
"prefill_chunk_size": 1024,
|
| 68 |
+
"sequence_length": 8192,
|
| 69 |
+
"speculation_length": 0,
|
| 70 |
+
"start_rank_id": 0,
|
| 71 |
+
"target": "trn1",
|
| 72 |
+
"torch_dtype": "bfloat16",
|
| 73 |
+
"tp_degree": 2
|
| 74 |
+
},
|
| 75 |
+
"num_attention_heads": 12,
|
| 76 |
+
"num_hidden_layers": 28,
|
| 77 |
+
"num_key_value_heads": 2,
|
| 78 |
+
"rms_norm_eps": 1e-06,
|
| 79 |
+
"rope_scaling": null,
|
| 80 |
+
"rope_theta": 1000000.0,
|
| 81 |
+
"sliding_window": null,
|
| 82 |
+
"tie_word_embeddings": true,
|
| 83 |
+
"use_cache": true,
|
| 84 |
+
"use_mrope": false,
|
| 85 |
+
"use_sliding_window": false,
|
| 86 |
+
"vocab_size": 151936
|
| 87 |
+
}
|
neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/nxdi_test_9154aabe-a2fc-4296-9aac-776ab26a2abb/compiler_workdir/Qwen2MLPWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afa3d904a568c03d056746bcdf8fbf470aad42628e8033149003f1d25a62bd0f
|
| 3 |
+
size 10111
|
neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/model.neff
ADDED
|
Binary file (62.5 kB). View file
|
|
|
neuronxcc-2.23.6484.0+3b612583/MODULE_00660dc06def0a86f076+f6e70309/wrapped_neff.hlo
ADDED
|
Binary file (64.5 kB). View file
|
|
|
neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b367f3493c9d08e4399192a7631108f52ed67d16e4356f7677a20a1a07decfa0
|
| 3 |
+
size 2083735
|
neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd4eab1e8e5b20a29ec14c1d1a7ff774ede9b2c569bc7ab2c965b9038f84da60
|
| 3 |
+
size 1506304
|
neuronxcc-2.23.6484.0+3b612583/MODULE_06962a2c830ca91c97ad+dae43e99/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80203e7ce8511b018a01d12165c49972f3698a76244dbcdf7d6a90c2c34f56dd
|
| 3 |
+
size 1662495
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/nxdi_test_c32815e8-e50a-4daa-9b53-d397c50c588d/compiler_workdir/Qwen2DecoderLayerOutputWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c4e16aae1dca0c586cc890bd30fdffc37d706370a3cdb7d79df31c07b1ed81c
|
| 3 |
+
size 64117
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dac046ac85f30f6586de29331c21a31ef41df27980d7075c88b2c49d97f15846
|
| 3 |
+
size 154624
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0f6388edb0a7baa22320+bec16cc7/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9efdf48a4ee7803d2b63c1036c7af618e39aa05c1774a92e0da3f8224cfc27b0
|
| 3 |
+
size 160976
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/nxdi_test_75555074-adcc-4380-a99f-54561544bf4a/compiler_workdir/Qwen2DecoderLayerOutputWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b61d78663a7b126bc1b1adec376f78204dcbac72b19566041bc2da988ba06e5
|
| 3 |
+
size 64117
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f720efbc6328d4a042cb797b170ab0fbe241b98ea79c398eae092955b720b47
|
| 3 |
+
size 154624
|
neuronxcc-2.23.6484.0+3b612583/MODULE_0fd8ebf24ec16df524e9+2dc01cc4/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a3e0083802950b5db6b61f0048220a29158a562b2e78ab4b3ad944c62922a6
|
| 3 |
+
size 160976
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/nxdi_test_c383e473-3b2f-43f1-943c-53f132561ee5/compiler_workdir/Qwen2DecoderLayerOutputWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d27d56d04e6caa699682c17e144292ba1fa6095012c96a5b79944a48c41dbf3
|
| 3 |
+
size 63938
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a1aaac636e8b6f20866794c7f04b0f9ae2d8e1bd5a7ec9fc21bcc8a5a973f2e
|
| 3 |
+
size 154624
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1275faa1a81a00b1f3b2+5cdfeea4/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e89b956b88c02baf1a5e73d550ec8b2a52d70d0e33267cc65a791552fc4de42
|
| 3 |
+
size 160976
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/nxdi_test_78a50206-8662-4353-8d18-0b73c0110200/compiler_workdir/Qwen2DecoderLayerOutputWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9ff0e8a07a92c7104809a1ff81d63e3f6a90c7ea4f0c6d31906f43b1e1186b7
|
| 3 |
+
size 63410
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8c985116437a23795ade4078ef06215b1ed1231f187125300a64f3905eab407
|
| 3 |
+
size 154624
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1596b431c3fb1bec4bba+c0327fb9/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c059910ac05ec9aee2644c63e851884a3e81245b5692c464bac89c8e45189da7
|
| 3 |
+
size 160976
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 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"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa0c0e8f1bdac1c56e90031145d2f61b64d2ca312b75b9a50e302828f10b8ca9
|
| 3 |
+
size 1829814
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1bc222d2fb6154936b4a+781055f7/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82989737f73a6468d88738a1f38a3807f96b981ddc71e58bf2630b0886da8f66
|
| 3 |
+
size 1526784
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/nxdi_test_65529bcd-8450-4655-937a-0e46eb0b5826/compiler_workdir/Qwen2DecoderLayerOutputWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6932ccfad4efda7a0147e902fd1ac28bc2f7338324cde8a9137e68a57a3015c6
|
| 3 |
+
size 63465
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bec3f7233a98a3d71d65139ee26721402420f55b0952622111b386f79c2f54d0
|
| 3 |
+
size 154624
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1cbb24ef6bf4ede345ce+dd3f38f3/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:038d9b63b9c202d20fc1bfe25a0027d35536720c10bc811961c230ae18b9c9bb
|
| 3 |
+
size 160976
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--verbose=35", "--logfile=/tmp/nxdi_test_af103f2a-d2d3-4ecf-9c6d-066af19024e6/compiler_workdir/Qwen2InputLayerNormWrapper/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/model.done
ADDED
|
File without changes
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1372ab5a673a96092cf56abf46a0b3f765a49d245116bc22e91b6b68880c078
|
| 3 |
+
size 2860
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/model.neff
ADDED
|
Binary file (42 kB). View file
|
|
|
neuronxcc-2.23.6484.0+3b612583/MODULE_1d815a61b4d307378fda+4dc1b68c/wrapped_neff.hlo
ADDED
|
Binary file (42.9 kB). View file
|
|
|