Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
521
jburtoft commited on
Commit
1b949c2
·
verified ·
1 Parent(s): b1292fc

Synchronizing local compiler cache.

Browse files
Files changed (14) hide show
  1. .gitattributes +4 -0
  2. neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/compile_flags.json +1 -0
  3. neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/model.done +0 -0
  4. neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/model.hlo_module.pb +3 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/model.neff +3 -0
  6. neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/compile_flags.json +1 -0
  7. neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/model.done +0 -0
  8. neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/model.hlo_module.pb +3 -0
  9. neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/model.neff +3 -0
  10. neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/wrapped_neff.hlo +3 -0
  11. neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/compile_flags.json +1 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/model.done +0 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/model.hlo_module.pb +3 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/model.neff +3 -0
.gitattributes CHANGED
@@ -10002,3 +10002,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_65a3f7722bfb2e950d7c/text_encoder/model.ne
10002
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_65a3f7722bfb2e950d7c/transformer/model.neuron filter=lfs diff=lfs merge=lfs -text
10003
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_65a3f7722bfb2e950d7c/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10004
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_65a3f7722bfb2e950d7c/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
10002
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_65a3f7722bfb2e950d7c/transformer/model.neuron filter=lfs diff=lfs merge=lfs -text
10003
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_65a3f7722bfb2e950d7c/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10004
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_65a3f7722bfb2e950d7c/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
10005
+ neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
10006
+ neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
10007
+ neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
10008
+ neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ad57ae6854d0a3520417b6f7dc2b79e9d321ed0965c94ca76188d7be6d7aa8
3
+ size 95868
neuronxcc-2.17.194.0+d312836f/MODULE_b572d80ed6676d2c7288+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96882fb5280edf1a8fad0dbc6f2f1cd88bd4d214a5223ad4a86a3ace466022f5
3
+ size 1106944
neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3202af945694533a1bd08dd7c134211aaac3519f8b171e1af82fdc318ee5745f
3
+ size 551467
neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a21d955f6d45060751b74e244290eeadc91c38c874d9ea7f2c52b1c31ad504e5
3
+ size 1403904
neuronxcc-2.17.194.0+d312836f/MODULE_be2b872eec6f56f9ff84+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81c2521509ba03724f88a0de3958dd6286aa7998cbcd8177abf6a88d5f334dc4
3
+ size 1500263
neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cbd53422d71f692c90847797015505816249f8890eef0a12bff6795cc982e618
3
+ size 494147
neuronxcc-2.17.194.0+d312836f/MODULE_eb173b807b030eb477f6+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f802c80a4d2a75bb062865adc9e9f0dd42fe8f9410c709db55a49bcfc8634a
3
+ size 4742144