Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
679
dacorvo HF Staff commited on
Commit
762c77c
·
verified ·
1 Parent(s): 322e074

Synchronizing local compiler cache.

Browse files
Files changed (18) hide show
  1. .gitattributes +5 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/compile_flags.json +1 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/model.done +0 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/model.hlo_module.pb +3 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/model.neff +3 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/wrapped_neff.hlo +3 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/compile_flags.json +1 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/model.done +0 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/model.hlo_module.pb +3 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/model.neff +3 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9ae5c24c58ede0b3d788+24129607/compile_flags.json +1 -0
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9ae5c24c58ede0b3d788+24129607/model.hlo_module.pb +3 -0
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9ae5c24c58ede0b3d788+24129607/model.log +3 -0
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/compile_flags.json +1 -0
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/model.done +0 -0
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/model.hlo_module.pb +3 -0
  17. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/model.neff +3 -0
  18. neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -12694,3 +12694,8 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_cef58634f78a7c3466a5+a02c3a36/wrapped_nef
12694
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa6d2c20168268e57204+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
12695
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa6d2c20168268e57204+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12696
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_b2d8112f00b8aaa845b4+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
12694
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa6d2c20168268e57204+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
12695
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_aa6d2c20168268e57204+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12696
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_b2d8112f00b8aaa845b4+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
12697
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
12698
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
12699
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
12700
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
12701
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+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-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb344c672a010536aa058ddd9a19cd7de40cb29e0b785ac541c8dd2fc630085f
3
+ size 102926602
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa72971b6176c9cc24105479e506fee31d57095d2c0d970e111f007bdb09ba3
3
+ size 7128064
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1e4aa96ffb69db7cad95+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c31de3643100e609ad801cba4f77490e1d6099dde7d02dfd84e6db22d6eaa44
3
+ size 7437033
neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a2eca49acbf033d9f4b3edc6c3b5267e41987cb20c6e58fc51b47aca7913f2
3
+ size 107319785
neuronxcc-2.21.18209.0+043b1bf7/MODULE_81835ddc6932ade9e981+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fea91765b69c34011972f2ff18bff610545d9c150edcfc9e1d3a163583c1c470
3
+ size 39793664
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9ae5c24c58ede0b3d788+24129607/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/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9ae5c24c58ede0b3d788+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b821815e6924737a059b602e29ce2afeeb7e655b08d4b5784cd825ea78a54ac
3
+ size 106099506
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9ae5c24c58ede0b3d788+24129607/model.log ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_9ae5c24c58ede0b3d788+24129607.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_9ae5c24c58ede0b3d788+24129607.neff', '--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/context_encoding/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: [XCG815] Estimated peak HBM usage (19.099GB) exceeds 16GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
2
+ 2025-11-06T01:53:12Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815] Estimated peak HBM usage (19.099GB) exceeds 16GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
3
+
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00f60e1302a36413e331034d2f4f85b0c157d035fd068c66597c0b299922a21
3
+ size 109160778
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1e3ba0fabe72a298ad25bcfe2263476a716fc79d4d5acf84dae4366f20b58c7
3
+ size 22559744
neuronxcc-2.21.18209.0+043b1bf7/MODULE_b9345244b4cca9acf84d+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad3f7a9a4bdb9d4319f733ac2d9132bac803a0d5ff880df2ecfd75e369e67a4c
3
+ size 22869116