Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- .gitattributes +72 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/88ab959ffd7f969e9ecf.json +59 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/866e4ae3016710258519.json +88 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/4d19457aee330abf74c2.json +165 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/bde8d1f238d097f95d53.json +165 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/granite/ibm-granite/granite-3.1-2b-instruct/88ab959ffd7f969e9ecf.json +59 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/phi3/microsoft/Phi-3.5-mini-instruct/bde8d1f238d097f95d53.json +165 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-Embedding-0.6B/866e4ae3016710258519.json +88 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/compile_flags.json +1 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.done +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.hlo_module.pb +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.neff +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/wrapped_neff.hlo +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/compile_flags.json +1 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.done +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.hlo_module.pb +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.neff +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/compile_flags.json +1 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.done +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.hlo_module.pb +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.neff +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/wrapped_neff.hlo +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/compile_flags.json +1 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.done +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.hlo_module.pb +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.neff +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/wrapped_neff.hlo +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_11301370888592189606+e30acd3a/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_14657035910656097540+e30acd3a/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_15128894797204950836+e30acd3a/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff +0 -0
.gitattributes
CHANGED
|
@@ -17193,3 +17193,75 @@ neuronxcc-2.21.33363.0+82129205/MODULE_bec56f8afdbf66a50c25+a02c3a36/wrapped_nef
|
|
| 17193 |
neuronxcc-2.21.33363.0+82129205/MODULE_e337d9bea67418c4cbfc+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17194 |
neuronxcc-2.21.33363.0+82129205/MODULE_e337d9bea67418c4cbfc+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17195 |
neuronxcc-2.21.33363.0+82129205/MODULE_e860112df381f8b3f4ae+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17193 |
neuronxcc-2.21.33363.0+82129205/MODULE_e337d9bea67418c4cbfc+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17194 |
neuronxcc-2.21.33363.0+82129205/MODULE_e337d9bea67418c4cbfc+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17195 |
neuronxcc-2.21.33363.0+82129205/MODULE_e860112df381f8b3f4ae+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17196 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17197 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17198 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17199 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17200 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17201 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17202 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17203 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_1bfa3dd1929fbcd69193+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17204 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_25ecfcd32b38ffcca9c6+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17205 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17206 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_264f116884a2b72bfd94+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17207 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_272f23df0029fc228e27+6e4949b4/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17208 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_30f9fb1c90d72ce5be20+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17209 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17210 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_35c78e406a558e46489f+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17211 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17212 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_3be023fb36d494480eab+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17213 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_3f20d1a2a58617b5c568+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17214 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_4371876575046bfaddbc+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17215 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17216 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_4a866a7ab3440bf5039c+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17217 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17218 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_4c340605e5cfcfb52aa0+4cce07ab/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17219 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17220 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_4e8633381936708d6422+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17221 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_5882b7576829bc99fe1e+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17222 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17223 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_5ca02efa566c733695c6+3ab2fb27/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17224 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17225 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_649c25ed694844adcb1e+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17226 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17227 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_6b4fc5b451fdfa1b744b+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17228 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17229 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_6e8fd65e06dcc6271828+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17230 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_731d30e8407c98f2d0ed+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17231 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_75a04de57ab666b70aff+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17232 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_76e92077ca40a96b12db+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17233 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17234 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_7d8253c434168957472d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17235 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17236 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_7ec08bf0fb6b63a494ce+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17237 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17238 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_8ec74b7503cb0a5e0b12+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17239 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_9efcdde20b63764672c5+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17240 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17241 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_b0696c18110a46d8a884+6f0a400d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17242 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17243 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_b671fe852f9096fe7aa3+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17244 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17245 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_b72fc7afaa1831a24a09+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17246 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17247 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_bde9ee2bb7e53f22e095+80d05c3f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17248 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_c6635e2179b5a4161da1+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17249 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17250 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_c69b5542e96ab576f244+755a2aef/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17251 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17252 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_ce61e92cac5a58aac125+4af285bc/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17253 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17254 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_d13ee67d85c8f49510c4+2dde74c7/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17255 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_d56f37f16ff55f594311+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17256 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17257 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_e8a43167f74176083689+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17258 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_ef6a56befefaaf69dc23+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17259 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_f0597be9cdf3f20234ea+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17260 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_f16e59ac0827406c000f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17261 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17262 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_f76d71fc849f0090bedd+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17263 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_f7d293fceac8bc3b694c+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17264 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_f8644b89d99409c828a0+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17265 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 17266 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_fadf125c58ba12884396+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 17267 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_fbd4adbd7e12955cf995+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/0cc25526e2cfc37a8875a3752f33c4d7505d8a07b869d0f3f41915cf6e763b74/88ab959ffd7f969e9ecf.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GraniteForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"attention_multiplier": 0.015625,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"embedding_multiplier": 12.0,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 2048,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 8192,
|
| 17 |
+
"logits_scaling": 8.0,
|
| 18 |
+
"max_position_embeddings": 131072,
|
| 19 |
+
"mlp_bias": false,
|
| 20 |
+
"model_type": "granite",
|
| 21 |
+
"neuron": {
|
| 22 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 23 |
+
"batch_size": 4,
|
| 24 |
+
"capacity_factor": null,
|
| 25 |
+
"checkpoint_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 26 |
+
"checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d",
|
| 27 |
+
"continuous_batching": true,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": true,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"max_batch_size": 4,
|
| 33 |
+
"max_context_length": 1024,
|
| 34 |
+
"max_topk": 256,
|
| 35 |
+
"n_active_tokens": 1024,
|
| 36 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 37 |
+
"on_device_sampling": true,
|
| 38 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 39 |
+
"output_logits": false,
|
| 40 |
+
"pp_degree": 1,
|
| 41 |
+
"prefill_chunk_size": 0,
|
| 42 |
+
"sequence_length": 1024,
|
| 43 |
+
"speculation_length": 0,
|
| 44 |
+
"start_rank_id": 0,
|
| 45 |
+
"target": "trn1",
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"tp_degree": 2
|
| 48 |
+
},
|
| 49 |
+
"num_attention_heads": 32,
|
| 50 |
+
"num_hidden_layers": 40,
|
| 51 |
+
"num_key_value_heads": 8,
|
| 52 |
+
"residual_multiplier": 0.22,
|
| 53 |
+
"rms_norm_eps": 1e-05,
|
| 54 |
+
"rope_scaling": null,
|
| 55 |
+
"rope_theta": 5000000.0,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 49155
|
| 59 |
+
}
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/60feecaa0c4c075e2f3e46a3f55d9a273f0ddd75a0ecf64e4ae27352e0819506/866e4ae3016710258519.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen3-Embedding-0.6B",
|
| 4 |
+
"_task": "feature-extraction",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"head_dim": 128,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_types": [
|
| 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 |
+
"full_attention",
|
| 44 |
+
"full_attention"
|
| 45 |
+
],
|
| 46 |
+
"max_position_embeddings": 32768,
|
| 47 |
+
"max_window_layers": 28,
|
| 48 |
+
"model_type": "qwen3",
|
| 49 |
+
"neuron": {
|
| 50 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 51 |
+
"batch_size": 4,
|
| 52 |
+
"capacity_factor": null,
|
| 53 |
+
"checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
|
| 54 |
+
"checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
|
| 55 |
+
"continuous_batching": false,
|
| 56 |
+
"ep_degree": 1,
|
| 57 |
+
"fused_qkv": true,
|
| 58 |
+
"glu_mlp": true,
|
| 59 |
+
"local_ranks_size": 2,
|
| 60 |
+
"max_batch_size": 4,
|
| 61 |
+
"max_context_length": 8192,
|
| 62 |
+
"max_topk": 256,
|
| 63 |
+
"n_active_tokens": 8192,
|
| 64 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 65 |
+
"on_device_sampling": false,
|
| 66 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 67 |
+
"output_logits": false,
|
| 68 |
+
"pp_degree": 1,
|
| 69 |
+
"prefill_chunk_size": 1024,
|
| 70 |
+
"sequence_length": 8192,
|
| 71 |
+
"speculation_length": 0,
|
| 72 |
+
"start_rank_id": 0,
|
| 73 |
+
"target": "trn1",
|
| 74 |
+
"torch_dtype": "bfloat16",
|
| 75 |
+
"tp_degree": 2
|
| 76 |
+
},
|
| 77 |
+
"num_attention_heads": 16,
|
| 78 |
+
"num_hidden_layers": 28,
|
| 79 |
+
"num_key_value_heads": 8,
|
| 80 |
+
"rms_norm_eps": 1e-06,
|
| 81 |
+
"rope_scaling": null,
|
| 82 |
+
"rope_theta": 1000000,
|
| 83 |
+
"sliding_window": null,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vocab_size": 151669
|
| 88 |
+
}
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/4d19457aee330abf74c2.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "microsoft/Phi-3.5-mini-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"auto_map": {
|
| 11 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 12 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 13 |
+
},
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"embd_pdrop": 0.0,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 3072,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 8192,
|
| 20 |
+
"max_position_embeddings": 131072,
|
| 21 |
+
"model_type": "phi3",
|
| 22 |
+
"neuron": {
|
| 23 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 24 |
+
"batch_size": 1,
|
| 25 |
+
"capacity_factor": null,
|
| 26 |
+
"checkpoint_id": "microsoft/Phi-3.5-mini-instruct",
|
| 27 |
+
"checkpoint_revision": "2fe192450127e6a83f7441aef6e3ca586c338b77",
|
| 28 |
+
"continuous_batching": false,
|
| 29 |
+
"ep_degree": 1,
|
| 30 |
+
"fused_qkv": true,
|
| 31 |
+
"glu_mlp": true,
|
| 32 |
+
"local_ranks_size": 2,
|
| 33 |
+
"max_batch_size": 1,
|
| 34 |
+
"max_context_length": 8192,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 8192,
|
| 37 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"prefill_chunk_size": 1024,
|
| 43 |
+
"sequence_length": 8192,
|
| 44 |
+
"speculation_length": 0,
|
| 45 |
+
"start_rank_id": 0,
|
| 46 |
+
"target": "trn1",
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"tp_degree": 2
|
| 49 |
+
},
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"original_max_position_embeddings": 4096,
|
| 54 |
+
"partial_rotary_factor": 1.0,
|
| 55 |
+
"resid_pdrop": 0.0,
|
| 56 |
+
"rms_norm_eps": 1e-05,
|
| 57 |
+
"rope_scaling": {
|
| 58 |
+
"long_factor": [
|
| 59 |
+
1.0800000429153442,
|
| 60 |
+
1.1100000143051147,
|
| 61 |
+
1.1399999856948853,
|
| 62 |
+
1.340000033378601,
|
| 63 |
+
1.5899999141693115,
|
| 64 |
+
1.600000023841858,
|
| 65 |
+
1.6200000047683716,
|
| 66 |
+
2.620000123977661,
|
| 67 |
+
3.2300000190734863,
|
| 68 |
+
3.2300000190734863,
|
| 69 |
+
4.789999961853027,
|
| 70 |
+
7.400000095367432,
|
| 71 |
+
7.700000286102295,
|
| 72 |
+
9.09000015258789,
|
| 73 |
+
12.199999809265137,
|
| 74 |
+
17.670000076293945,
|
| 75 |
+
24.46000099182129,
|
| 76 |
+
28.57000160217285,
|
| 77 |
+
30.420001983642578,
|
| 78 |
+
30.840002059936523,
|
| 79 |
+
32.590003967285156,
|
| 80 |
+
32.93000411987305,
|
| 81 |
+
42.320003509521484,
|
| 82 |
+
44.96000289916992,
|
| 83 |
+
50.340003967285156,
|
| 84 |
+
50.45000457763672,
|
| 85 |
+
57.55000305175781,
|
| 86 |
+
57.93000411987305,
|
| 87 |
+
58.21000289916992,
|
| 88 |
+
60.1400032043457,
|
| 89 |
+
62.61000442504883,
|
| 90 |
+
62.62000274658203,
|
| 91 |
+
62.71000289916992,
|
| 92 |
+
63.1400032043457,
|
| 93 |
+
63.1400032043457,
|
| 94 |
+
63.77000427246094,
|
| 95 |
+
63.93000411987305,
|
| 96 |
+
63.96000289916992,
|
| 97 |
+
63.970001220703125,
|
| 98 |
+
64.02999877929688,
|
| 99 |
+
64.06999969482422,
|
| 100 |
+
64.08000183105469,
|
| 101 |
+
64.12000274658203,
|
| 102 |
+
64.41000366210938,
|
| 103 |
+
64.4800033569336,
|
| 104 |
+
64.51000213623047,
|
| 105 |
+
64.52999877929688,
|
| 106 |
+
64.83999633789062
|
| 107 |
+
],
|
| 108 |
+
"short_factor": [
|
| 109 |
+
1.0,
|
| 110 |
+
1.0199999809265137,
|
| 111 |
+
1.0299999713897705,
|
| 112 |
+
1.0299999713897705,
|
| 113 |
+
1.0499999523162842,
|
| 114 |
+
1.0499999523162842,
|
| 115 |
+
1.0499999523162842,
|
| 116 |
+
1.0499999523162842,
|
| 117 |
+
1.0499999523162842,
|
| 118 |
+
1.0699999332427979,
|
| 119 |
+
1.0999999046325684,
|
| 120 |
+
1.1099998950958252,
|
| 121 |
+
1.1599998474121094,
|
| 122 |
+
1.1599998474121094,
|
| 123 |
+
1.1699998378753662,
|
| 124 |
+
1.2899998426437378,
|
| 125 |
+
1.339999794960022,
|
| 126 |
+
1.679999828338623,
|
| 127 |
+
1.7899998426437378,
|
| 128 |
+
1.8199998140335083,
|
| 129 |
+
1.8499997854232788,
|
| 130 |
+
1.8799997568130493,
|
| 131 |
+
1.9099997282028198,
|
| 132 |
+
1.9399996995925903,
|
| 133 |
+
1.9899996519088745,
|
| 134 |
+
2.0199997425079346,
|
| 135 |
+
2.0199997425079346,
|
| 136 |
+
2.0199997425079346,
|
| 137 |
+
2.0199997425079346,
|
| 138 |
+
2.0199997425079346,
|
| 139 |
+
2.0199997425079346,
|
| 140 |
+
2.0299997329711914,
|
| 141 |
+
2.0299997329711914,
|
| 142 |
+
2.0299997329711914,
|
| 143 |
+
2.0299997329711914,
|
| 144 |
+
2.0299997329711914,
|
| 145 |
+
2.0299997329711914,
|
| 146 |
+
2.0299997329711914,
|
| 147 |
+
2.0299997329711914,
|
| 148 |
+
2.0299997329711914,
|
| 149 |
+
2.0799996852874756,
|
| 150 |
+
2.0899996757507324,
|
| 151 |
+
2.189999580383301,
|
| 152 |
+
2.2199995517730713,
|
| 153 |
+
2.5899994373321533,
|
| 154 |
+
2.729999542236328,
|
| 155 |
+
2.749999523162842,
|
| 156 |
+
2.8399994373321533
|
| 157 |
+
],
|
| 158 |
+
"type": "longrope"
|
| 159 |
+
},
|
| 160 |
+
"rope_theta": 10000.0,
|
| 161 |
+
"sliding_window": 262144,
|
| 162 |
+
"tie_word_embeddings": false,
|
| 163 |
+
"use_cache": true,
|
| 164 |
+
"vocab_size": 32064
|
| 165 |
+
}
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/8c90ac2593ed0b7f1ecb60e82cb184fb11f2ea640befa1cc7b10766a5c02525d/bde8d1f238d097f95d53.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "microsoft/Phi-3.5-mini-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"auto_map": {
|
| 11 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 12 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 13 |
+
},
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"embd_pdrop": 0.0,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 3072,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 8192,
|
| 20 |
+
"max_position_embeddings": 131072,
|
| 21 |
+
"model_type": "phi3",
|
| 22 |
+
"neuron": {
|
| 23 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 24 |
+
"batch_size": 4,
|
| 25 |
+
"capacity_factor": null,
|
| 26 |
+
"checkpoint_id": "microsoft/Phi-3.5-mini-instruct",
|
| 27 |
+
"checkpoint_revision": "2fe192450127e6a83f7441aef6e3ca586c338b77",
|
| 28 |
+
"continuous_batching": true,
|
| 29 |
+
"ep_degree": 1,
|
| 30 |
+
"fused_qkv": true,
|
| 31 |
+
"glu_mlp": true,
|
| 32 |
+
"local_ranks_size": 2,
|
| 33 |
+
"max_batch_size": 4,
|
| 34 |
+
"max_context_length": 1024,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 1024,
|
| 37 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"prefill_chunk_size": 0,
|
| 43 |
+
"sequence_length": 1024,
|
| 44 |
+
"speculation_length": 0,
|
| 45 |
+
"start_rank_id": 0,
|
| 46 |
+
"target": "trn1",
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"tp_degree": 2
|
| 49 |
+
},
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"original_max_position_embeddings": 4096,
|
| 54 |
+
"partial_rotary_factor": 1.0,
|
| 55 |
+
"resid_pdrop": 0.0,
|
| 56 |
+
"rms_norm_eps": 1e-05,
|
| 57 |
+
"rope_scaling": {
|
| 58 |
+
"long_factor": [
|
| 59 |
+
1.0800000429153442,
|
| 60 |
+
1.1100000143051147,
|
| 61 |
+
1.1399999856948853,
|
| 62 |
+
1.340000033378601,
|
| 63 |
+
1.5899999141693115,
|
| 64 |
+
1.600000023841858,
|
| 65 |
+
1.6200000047683716,
|
| 66 |
+
2.620000123977661,
|
| 67 |
+
3.2300000190734863,
|
| 68 |
+
3.2300000190734863,
|
| 69 |
+
4.789999961853027,
|
| 70 |
+
7.400000095367432,
|
| 71 |
+
7.700000286102295,
|
| 72 |
+
9.09000015258789,
|
| 73 |
+
12.199999809265137,
|
| 74 |
+
17.670000076293945,
|
| 75 |
+
24.46000099182129,
|
| 76 |
+
28.57000160217285,
|
| 77 |
+
30.420001983642578,
|
| 78 |
+
30.840002059936523,
|
| 79 |
+
32.590003967285156,
|
| 80 |
+
32.93000411987305,
|
| 81 |
+
42.320003509521484,
|
| 82 |
+
44.96000289916992,
|
| 83 |
+
50.340003967285156,
|
| 84 |
+
50.45000457763672,
|
| 85 |
+
57.55000305175781,
|
| 86 |
+
57.93000411987305,
|
| 87 |
+
58.21000289916992,
|
| 88 |
+
60.1400032043457,
|
| 89 |
+
62.61000442504883,
|
| 90 |
+
62.62000274658203,
|
| 91 |
+
62.71000289916992,
|
| 92 |
+
63.1400032043457,
|
| 93 |
+
63.1400032043457,
|
| 94 |
+
63.77000427246094,
|
| 95 |
+
63.93000411987305,
|
| 96 |
+
63.96000289916992,
|
| 97 |
+
63.970001220703125,
|
| 98 |
+
64.02999877929688,
|
| 99 |
+
64.06999969482422,
|
| 100 |
+
64.08000183105469,
|
| 101 |
+
64.12000274658203,
|
| 102 |
+
64.41000366210938,
|
| 103 |
+
64.4800033569336,
|
| 104 |
+
64.51000213623047,
|
| 105 |
+
64.52999877929688,
|
| 106 |
+
64.83999633789062
|
| 107 |
+
],
|
| 108 |
+
"short_factor": [
|
| 109 |
+
1.0,
|
| 110 |
+
1.0199999809265137,
|
| 111 |
+
1.0299999713897705,
|
| 112 |
+
1.0299999713897705,
|
| 113 |
+
1.0499999523162842,
|
| 114 |
+
1.0499999523162842,
|
| 115 |
+
1.0499999523162842,
|
| 116 |
+
1.0499999523162842,
|
| 117 |
+
1.0499999523162842,
|
| 118 |
+
1.0699999332427979,
|
| 119 |
+
1.0999999046325684,
|
| 120 |
+
1.1099998950958252,
|
| 121 |
+
1.1599998474121094,
|
| 122 |
+
1.1599998474121094,
|
| 123 |
+
1.1699998378753662,
|
| 124 |
+
1.2899998426437378,
|
| 125 |
+
1.339999794960022,
|
| 126 |
+
1.679999828338623,
|
| 127 |
+
1.7899998426437378,
|
| 128 |
+
1.8199998140335083,
|
| 129 |
+
1.8499997854232788,
|
| 130 |
+
1.8799997568130493,
|
| 131 |
+
1.9099997282028198,
|
| 132 |
+
1.9399996995925903,
|
| 133 |
+
1.9899996519088745,
|
| 134 |
+
2.0199997425079346,
|
| 135 |
+
2.0199997425079346,
|
| 136 |
+
2.0199997425079346,
|
| 137 |
+
2.0199997425079346,
|
| 138 |
+
2.0199997425079346,
|
| 139 |
+
2.0199997425079346,
|
| 140 |
+
2.0299997329711914,
|
| 141 |
+
2.0299997329711914,
|
| 142 |
+
2.0299997329711914,
|
| 143 |
+
2.0299997329711914,
|
| 144 |
+
2.0299997329711914,
|
| 145 |
+
2.0299997329711914,
|
| 146 |
+
2.0299997329711914,
|
| 147 |
+
2.0299997329711914,
|
| 148 |
+
2.0299997329711914,
|
| 149 |
+
2.0799996852874756,
|
| 150 |
+
2.0899996757507324,
|
| 151 |
+
2.189999580383301,
|
| 152 |
+
2.2199995517730713,
|
| 153 |
+
2.5899994373321533,
|
| 154 |
+
2.729999542236328,
|
| 155 |
+
2.749999523162842,
|
| 156 |
+
2.8399994373321533
|
| 157 |
+
],
|
| 158 |
+
"type": "longrope"
|
| 159 |
+
},
|
| 160 |
+
"rope_theta": 10000.0,
|
| 161 |
+
"sliding_window": 262144,
|
| 162 |
+
"tie_word_embeddings": false,
|
| 163 |
+
"use_cache": true,
|
| 164 |
+
"vocab_size": 32064
|
| 165 |
+
}
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/granite/ibm-granite/granite-3.1-2b-instruct/88ab959ffd7f969e9ecf.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"GraniteForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.1,
|
| 10 |
+
"attention_multiplier": 0.015625,
|
| 11 |
+
"dtype": "bfloat16",
|
| 12 |
+
"embedding_multiplier": 12.0,
|
| 13 |
+
"hidden_act": "silu",
|
| 14 |
+
"hidden_size": 2048,
|
| 15 |
+
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 8192,
|
| 17 |
+
"logits_scaling": 8.0,
|
| 18 |
+
"max_position_embeddings": 131072,
|
| 19 |
+
"mlp_bias": false,
|
| 20 |
+
"model_type": "granite",
|
| 21 |
+
"neuron": {
|
| 22 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 23 |
+
"batch_size": 4,
|
| 24 |
+
"capacity_factor": null,
|
| 25 |
+
"checkpoint_id": "ibm-granite/granite-3.1-2b-instruct",
|
| 26 |
+
"checkpoint_revision": "bbc2aed595bd38bd770263dc3ab831db9794441d",
|
| 27 |
+
"continuous_batching": true,
|
| 28 |
+
"ep_degree": 1,
|
| 29 |
+
"fused_qkv": true,
|
| 30 |
+
"glu_mlp": true,
|
| 31 |
+
"local_ranks_size": 2,
|
| 32 |
+
"max_batch_size": 4,
|
| 33 |
+
"max_context_length": 1024,
|
| 34 |
+
"max_topk": 256,
|
| 35 |
+
"n_active_tokens": 1024,
|
| 36 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 37 |
+
"on_device_sampling": true,
|
| 38 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 39 |
+
"output_logits": false,
|
| 40 |
+
"pp_degree": 1,
|
| 41 |
+
"prefill_chunk_size": 0,
|
| 42 |
+
"sequence_length": 1024,
|
| 43 |
+
"speculation_length": 0,
|
| 44 |
+
"start_rank_id": 0,
|
| 45 |
+
"target": "trn1",
|
| 46 |
+
"torch_dtype": "bfloat16",
|
| 47 |
+
"tp_degree": 2
|
| 48 |
+
},
|
| 49 |
+
"num_attention_heads": 32,
|
| 50 |
+
"num_hidden_layers": 40,
|
| 51 |
+
"num_key_value_heads": 8,
|
| 52 |
+
"residual_multiplier": 0.22,
|
| 53 |
+
"rms_norm_eps": 1e-05,
|
| 54 |
+
"rope_scaling": null,
|
| 55 |
+
"rope_theta": 5000000.0,
|
| 56 |
+
"tie_word_embeddings": true,
|
| 57 |
+
"use_cache": true,
|
| 58 |
+
"vocab_size": 49155
|
| 59 |
+
}
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/phi3/microsoft/Phi-3.5-mini-instruct/bde8d1f238d097f95d53.json
ADDED
|
@@ -0,0 +1,165 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "microsoft/Phi-3.5-mini-instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Phi3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"auto_map": {
|
| 11 |
+
"AutoConfig": "configuration_phi3.Phi3Config",
|
| 12 |
+
"AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
|
| 13 |
+
},
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"embd_pdrop": 0.0,
|
| 16 |
+
"hidden_act": "silu",
|
| 17 |
+
"hidden_size": 3072,
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 8192,
|
| 20 |
+
"max_position_embeddings": 131072,
|
| 21 |
+
"model_type": "phi3",
|
| 22 |
+
"neuron": {
|
| 23 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 24 |
+
"batch_size": 4,
|
| 25 |
+
"capacity_factor": null,
|
| 26 |
+
"checkpoint_id": "microsoft/Phi-3.5-mini-instruct",
|
| 27 |
+
"checkpoint_revision": "2fe192450127e6a83f7441aef6e3ca586c338b77",
|
| 28 |
+
"continuous_batching": true,
|
| 29 |
+
"ep_degree": 1,
|
| 30 |
+
"fused_qkv": true,
|
| 31 |
+
"glu_mlp": true,
|
| 32 |
+
"local_ranks_size": 2,
|
| 33 |
+
"max_batch_size": 4,
|
| 34 |
+
"max_context_length": 1024,
|
| 35 |
+
"max_topk": 256,
|
| 36 |
+
"n_active_tokens": 1024,
|
| 37 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 38 |
+
"on_device_sampling": true,
|
| 39 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 40 |
+
"output_logits": false,
|
| 41 |
+
"pp_degree": 1,
|
| 42 |
+
"prefill_chunk_size": 0,
|
| 43 |
+
"sequence_length": 1024,
|
| 44 |
+
"speculation_length": 0,
|
| 45 |
+
"start_rank_id": 0,
|
| 46 |
+
"target": "trn1",
|
| 47 |
+
"torch_dtype": "bfloat16",
|
| 48 |
+
"tp_degree": 2
|
| 49 |
+
},
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"original_max_position_embeddings": 4096,
|
| 54 |
+
"partial_rotary_factor": 1.0,
|
| 55 |
+
"resid_pdrop": 0.0,
|
| 56 |
+
"rms_norm_eps": 1e-05,
|
| 57 |
+
"rope_scaling": {
|
| 58 |
+
"long_factor": [
|
| 59 |
+
1.0800000429153442,
|
| 60 |
+
1.1100000143051147,
|
| 61 |
+
1.1399999856948853,
|
| 62 |
+
1.340000033378601,
|
| 63 |
+
1.5899999141693115,
|
| 64 |
+
1.600000023841858,
|
| 65 |
+
1.6200000047683716,
|
| 66 |
+
2.620000123977661,
|
| 67 |
+
3.2300000190734863,
|
| 68 |
+
3.2300000190734863,
|
| 69 |
+
4.789999961853027,
|
| 70 |
+
7.400000095367432,
|
| 71 |
+
7.700000286102295,
|
| 72 |
+
9.09000015258789,
|
| 73 |
+
12.199999809265137,
|
| 74 |
+
17.670000076293945,
|
| 75 |
+
24.46000099182129,
|
| 76 |
+
28.57000160217285,
|
| 77 |
+
30.420001983642578,
|
| 78 |
+
30.840002059936523,
|
| 79 |
+
32.590003967285156,
|
| 80 |
+
32.93000411987305,
|
| 81 |
+
42.320003509521484,
|
| 82 |
+
44.96000289916992,
|
| 83 |
+
50.340003967285156,
|
| 84 |
+
50.45000457763672,
|
| 85 |
+
57.55000305175781,
|
| 86 |
+
57.93000411987305,
|
| 87 |
+
58.21000289916992,
|
| 88 |
+
60.1400032043457,
|
| 89 |
+
62.61000442504883,
|
| 90 |
+
62.62000274658203,
|
| 91 |
+
62.71000289916992,
|
| 92 |
+
63.1400032043457,
|
| 93 |
+
63.1400032043457,
|
| 94 |
+
63.77000427246094,
|
| 95 |
+
63.93000411987305,
|
| 96 |
+
63.96000289916992,
|
| 97 |
+
63.970001220703125,
|
| 98 |
+
64.02999877929688,
|
| 99 |
+
64.06999969482422,
|
| 100 |
+
64.08000183105469,
|
| 101 |
+
64.12000274658203,
|
| 102 |
+
64.41000366210938,
|
| 103 |
+
64.4800033569336,
|
| 104 |
+
64.51000213623047,
|
| 105 |
+
64.52999877929688,
|
| 106 |
+
64.83999633789062
|
| 107 |
+
],
|
| 108 |
+
"short_factor": [
|
| 109 |
+
1.0,
|
| 110 |
+
1.0199999809265137,
|
| 111 |
+
1.0299999713897705,
|
| 112 |
+
1.0299999713897705,
|
| 113 |
+
1.0499999523162842,
|
| 114 |
+
1.0499999523162842,
|
| 115 |
+
1.0499999523162842,
|
| 116 |
+
1.0499999523162842,
|
| 117 |
+
1.0499999523162842,
|
| 118 |
+
1.0699999332427979,
|
| 119 |
+
1.0999999046325684,
|
| 120 |
+
1.1099998950958252,
|
| 121 |
+
1.1599998474121094,
|
| 122 |
+
1.1599998474121094,
|
| 123 |
+
1.1699998378753662,
|
| 124 |
+
1.2899998426437378,
|
| 125 |
+
1.339999794960022,
|
| 126 |
+
1.679999828338623,
|
| 127 |
+
1.7899998426437378,
|
| 128 |
+
1.8199998140335083,
|
| 129 |
+
1.8499997854232788,
|
| 130 |
+
1.8799997568130493,
|
| 131 |
+
1.9099997282028198,
|
| 132 |
+
1.9399996995925903,
|
| 133 |
+
1.9899996519088745,
|
| 134 |
+
2.0199997425079346,
|
| 135 |
+
2.0199997425079346,
|
| 136 |
+
2.0199997425079346,
|
| 137 |
+
2.0199997425079346,
|
| 138 |
+
2.0199997425079346,
|
| 139 |
+
2.0199997425079346,
|
| 140 |
+
2.0299997329711914,
|
| 141 |
+
2.0299997329711914,
|
| 142 |
+
2.0299997329711914,
|
| 143 |
+
2.0299997329711914,
|
| 144 |
+
2.0299997329711914,
|
| 145 |
+
2.0299997329711914,
|
| 146 |
+
2.0299997329711914,
|
| 147 |
+
2.0299997329711914,
|
| 148 |
+
2.0299997329711914,
|
| 149 |
+
2.0799996852874756,
|
| 150 |
+
2.0899996757507324,
|
| 151 |
+
2.189999580383301,
|
| 152 |
+
2.2199995517730713,
|
| 153 |
+
2.5899994373321533,
|
| 154 |
+
2.729999542236328,
|
| 155 |
+
2.749999523162842,
|
| 156 |
+
2.8399994373321533
|
| 157 |
+
],
|
| 158 |
+
"type": "longrope"
|
| 159 |
+
},
|
| 160 |
+
"rope_theta": 10000.0,
|
| 161 |
+
"sliding_window": 262144,
|
| 162 |
+
"tie_word_embeddings": false,
|
| 163 |
+
"use_cache": true,
|
| 164 |
+
"vocab_size": 32064
|
| 165 |
+
}
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev3/qwen3/Qwen/Qwen3-Embedding-0.6B/866e4ae3016710258519.json
ADDED
|
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen3-Embedding-0.6B",
|
| 4 |
+
"_task": "feature-extraction",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"head_dim": 128,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_types": [
|
| 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 |
+
"full_attention",
|
| 44 |
+
"full_attention"
|
| 45 |
+
],
|
| 46 |
+
"max_position_embeddings": 32768,
|
| 47 |
+
"max_window_layers": 28,
|
| 48 |
+
"model_type": "qwen3",
|
| 49 |
+
"neuron": {
|
| 50 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 51 |
+
"batch_size": 4,
|
| 52 |
+
"capacity_factor": null,
|
| 53 |
+
"checkpoint_id": "Qwen/Qwen3-Embedding-0.6B",
|
| 54 |
+
"checkpoint_revision": "c54f2e6e80b2d7b7de06f51cec4959f6b3e03418",
|
| 55 |
+
"continuous_batching": false,
|
| 56 |
+
"ep_degree": 1,
|
| 57 |
+
"fused_qkv": true,
|
| 58 |
+
"glu_mlp": true,
|
| 59 |
+
"local_ranks_size": 2,
|
| 60 |
+
"max_batch_size": 4,
|
| 61 |
+
"max_context_length": 8192,
|
| 62 |
+
"max_topk": 256,
|
| 63 |
+
"n_active_tokens": 8192,
|
| 64 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 65 |
+
"on_device_sampling": false,
|
| 66 |
+
"optimum_neuron_version": "0.4.6.dev3",
|
| 67 |
+
"output_logits": false,
|
| 68 |
+
"pp_degree": 1,
|
| 69 |
+
"prefill_chunk_size": 1024,
|
| 70 |
+
"sequence_length": 8192,
|
| 71 |
+
"speculation_length": 0,
|
| 72 |
+
"start_rank_id": 0,
|
| 73 |
+
"target": "trn1",
|
| 74 |
+
"torch_dtype": "bfloat16",
|
| 75 |
+
"tp_degree": 2
|
| 76 |
+
},
|
| 77 |
+
"num_attention_heads": 16,
|
| 78 |
+
"num_hidden_layers": 28,
|
| 79 |
+
"num_key_value_heads": 8,
|
| 80 |
+
"rms_norm_eps": 1e-06,
|
| 81 |
+
"rope_scaling": null,
|
| 82 |
+
"rope_theta": 1000000,
|
| 83 |
+
"sliding_window": null,
|
| 84 |
+
"tie_word_embeddings": true,
|
| 85 |
+
"use_cache": true,
|
| 86 |
+
"use_sliding_window": false,
|
| 87 |
+
"vocab_size": 151669
|
| 88 |
+
}
|
neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/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", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6070ba301fdd09bd8986151e94c7b92ce7819a1d22c851ff55373b6d132bdd5
|
| 3 |
+
size 87331
|
neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3feae7061a6e87b40cf794818cfd435e42b033c7f8380972829f873fa9787e8c
|
| 3 |
+
size 236544
|
neuronxcc-2.21.33363.0+82129205/MODULE_034cf87f477c882b257f+a02c3a36/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e52cf7dc0e5f6cb7a27b7f359a858711690d867d08124c333abb5daa645c4718
|
| 3 |
+
size 244847
|
neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
|
neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e8239944f5c78d314d34c0e8ea62975adcc12d846f485c3c5fea351b127db89
|
| 3 |
+
size 99591
|
neuronxcc-2.21.33363.0+82129205/MODULE_04cec4dcda7910e7fb2e+283df001/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd41c9c13e10e8bde7c89554bd777f6c1c86a48d2df0bf4e2076c3086c4b5dbf
|
| 3 |
+
size 410624
|
neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/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", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3995113b9941789a06c77ea7f12cea66ce8f84e71f1c545e6fb307d19d5b330
|
| 3 |
+
size 89962
|
neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20e0ebd7df8002034ca5710ae915e4bbd03ea1897ed60c71417a46c80cfce934
|
| 3 |
+
size 287744
|
neuronxcc-2.21.33363.0+82129205/MODULE_0b9974a2d1726da77b0a+a02c3a36/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a17b050bc6ff253b2ed29a8a618ec985673ec3d3ccc738af645ab113f498de73
|
| 3 |
+
size 296049
|
neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/compile_flags.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
["--target=trn1", "--enable-saturate-infinity", "--auto-cast=none", "--model-type=transformer", "-O1", "--logfile=/tmp/nxdi_test_c7c088ba-1995-4e62-851a-c774a6069131/compiler_workdir/NeuronRMSNorm/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c774c6626fc91684e924b843c1fe807dadbbac6d8a8e19443663b43c13eac35
|
| 3 |
+
size 1165
|
neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d0af0e67de0c158c397a503ee4c1e80ca6bbfe89239565e96795dd3a821030e6
|
| 3 |
+
size 103424
|
neuronxcc-2.21.33363.0+82129205/MODULE_0c504f5fe9366071df6f+2b70e3a5/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f424802b4fb9ab1e755d51541e72053fa1436b169b387d6fe9f2c368c69f0079
|
| 3 |
+
size 104320
|
neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10244305442015770634+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10606948783918825529+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10645643398657092095+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10661660426924300837+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_10746122569655005679+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_11086318750207148626+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_11301370888592189606+e30acd3a/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 246784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7e3ebadfc05c2572babe3aff125e581b50060d2ddf96e09ee3a4a0b55c19375
|
| 3 |
size 246784
|
neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_11909310600244571805+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_11933818254123612383+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_1210392327607194823+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13102010590082783346+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13475273426270778455+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13728813963059599796+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_13783872956654054643+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14097776130612710282+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14155105943057125178+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14173682194645188821+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14274833313744358348+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14469716438804935215+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_14657035910656097540+e30acd3a/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 123904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:703a7e8e3848965928554cadbd5d5b8934c7f3d55d17152862a9579a043afa2e
|
| 3 |
size 123904
|
neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_14739672283771660808+e30acd3a/model.neff differ
|
|
|
neuronxcc-2.21.33363.0+82129205/MODULE_15128894797204950836+e30acd3a/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 113664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2bfe04556f19754f56e7322a2686563fef9d0fce7d3ab6fee4641cecbaef16c
|
| 3 |
size 113664
|
neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff
CHANGED
|
Binary files a/neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff and b/neuronxcc-2.21.33363.0+82129205/MODULE_15557971880365771457+e30acd3a/model.neff differ
|
|
|