Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
dacorvo HF Staff commited on
Commit
4202ee6
·
verified ·
1 Parent(s): 9b9d03c

Synchronizing local compiler cache.

Browse files
Files changed (41) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/1cab6edbf167cfd815cf.json +77 -0
  3. neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+bfe5714b/compile_flags.json +1 -0
  4. neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+bfe5714b/model.done +0 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+bfe5714b/model.hlo_module.pb +3 -0
  6. neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+bfe5714b/model.neff +3 -0
  7. neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+431f5505/compile_flags.json +1 -0
  8. neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+431f5505/model.done +0 -0
  9. neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+431f5505/model.hlo_module.pb +3 -0
  10. neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+431f5505/model.neff +3 -0
  11. neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/compile_flags.json +1 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/model.done +0 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/model.hlo_module.pb +3 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/model.neff +3 -0
  15. neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/wrapped_neff.hlo +3 -0
  16. neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+431f5505/compile_flags.json +1 -0
  17. neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+431f5505/model.done +0 -0
  18. neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+431f5505/model.hlo_module.pb +3 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+431f5505/model.neff +3 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+bfe5714b/compile_flags.json +1 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+bfe5714b/model.done +0 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+bfe5714b/model.hlo_module.pb +3 -0
  23. neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+bfe5714b/model.neff +3 -0
  24. neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+bfe5714b/compile_flags.json +1 -0
  25. neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+bfe5714b/model.done +0 -0
  26. neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+bfe5714b/model.hlo_module.pb +3 -0
  27. neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+bfe5714b/model.neff +3 -0
  28. neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/compile_flags.json +1 -0
  29. neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/model.done +0 -0
  30. neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/model.hlo_module.pb +3 -0
  31. neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/model.neff +3 -0
  32. neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/wrapped_neff.hlo +3 -0
  33. neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/compile_flags.json +1 -0
  34. neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/model.done +0 -0
  35. neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/model.hlo_module.pb +3 -0
  36. neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/model.neff +3 -0
  37. neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/wrapped_neff.hlo +3 -0
  38. neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+431f5505/compile_flags.json +1 -0
  39. neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+431f5505/model.done +0 -0
  40. neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+431f5505/model.hlo_module.pb +3 -0
  41. neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+431f5505/model.neff +3 -0
.gitattributes CHANGED
@@ -2913,3 +2913,15 @@ neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.neff fi
2913
  neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2914
  neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
2915
  neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
2913
  neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2914
  neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
2915
  neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2916
+ neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2917
+ neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
2918
+ neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2919
+ neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2920
+ neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
2921
+ neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2922
+ neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2923
+ neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2924
+ neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2925
+ neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2926
+ neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2927
+ neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/phi3/microsoft/Phi-3-mini-4k-instruct/1cab6edbf167cfd815cf.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "microsoft/Phi-3-mini-4k-instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Phi3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "auto_map": {
11
+ "AutoConfig": "microsoft/Phi-3-mini-4k-instruct--configuration_phi3.Phi3Config",
12
+ "AutoModelForCausalLM": "microsoft/Phi-3-mini-4k-instruct--modeling_phi3.Phi3ForCausalLM"
13
+ },
14
+ "embd_pdrop": 0.0,
15
+ "hidden_act": "silu",
16
+ "hidden_size": 3072,
17
+ "initializer_range": 0.02,
18
+ "intermediate_size": 8192,
19
+ "max_position_embeddings": 4096,
20
+ "model_type": "phi3",
21
+ "neuron": {
22
+ "_serialized_key": "NxDNeuronConfig",
23
+ "async_mode": false,
24
+ "attn_kernel_enabled": false,
25
+ "batch_size": 4,
26
+ "capacity_factor": null,
27
+ "cc_pipeline_tiling_factor": 2,
28
+ "checkpoint_id": "microsoft/Phi-3-mini-4k-instruct",
29
+ "checkpoint_revision": "0a67737cc96d2554230f90338b163bc6380a2a85",
30
+ "continuous_batching": true,
31
+ "enable_bucketing": false,
32
+ "ep_degree": 1,
33
+ "flash_decoding_enabled": false,
34
+ "fused_qkv": true,
35
+ "glu_mlp": true,
36
+ "is_chunked_prefill": false,
37
+ "local_ranks_size": 2,
38
+ "logical_nc_config": 1,
39
+ "max_batch_size": 4,
40
+ "max_context_length": 4096,
41
+ "max_topk": 256,
42
+ "mlp_kernel_enabled": false,
43
+ "mlp_kernel_fuse_residual_add": false,
44
+ "n_active_tokens": 4096,
45
+ "neuronxcc_version": "2.17.194.0+d312836f",
46
+ "num_cores_per_group": 1,
47
+ "on_device_sampling": false,
48
+ "optimum_neuron_version": "0.3.0.dev0",
49
+ "output_logits": false,
50
+ "padding_side": "right",
51
+ "pp_degree": 1,
52
+ "qk_layernorm": false,
53
+ "qkv_kernel_enabled": false,
54
+ "rpl_reduce_dtype": "bfloat16",
55
+ "sequence_length": 4096,
56
+ "sequence_parallel_enabled": false,
57
+ "speculation_length": 0,
58
+ "start_rank_id": 0,
59
+ "target": null,
60
+ "torch_dtype": "bfloat16",
61
+ "tp_degree": 2,
62
+ "vocab_parallel": false
63
+ },
64
+ "num_attention_heads": 32,
65
+ "num_hidden_layers": 32,
66
+ "num_key_value_heads": 32,
67
+ "original_max_position_embeddings": 4096,
68
+ "partial_rotary_factor": 1.0,
69
+ "resid_pdrop": 0.0,
70
+ "rms_norm_eps": 1e-05,
71
+ "rope_scaling": null,
72
+ "rope_theta": 10000.0,
73
+ "sliding_window": 2047,
74
+ "tie_word_embeddings": false,
75
+ "use_cache": true,
76
+ "vocab_size": 32064
77
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+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_4e28e03424738806f8ca+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc52c78a504427be98bec0efa83bc40a4177085a749ee7d7925ee0136db6d2ce
3
+ size 842826
neuronxcc-2.17.194.0+d312836f/MODULE_4e28e03424738806f8ca+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa7858cc532af479f3724179495879fea25ddc59a0a0c269f88056ab467020ac
3
+ size 6503424
neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+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_71d6f1724eb9ca6bbf34+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fb7b29b350aa05a5de71272d48a2dda64315a6c16f61d123a3ea9ebb02a0878
3
+ size 136006
neuronxcc-2.17.194.0+d312836f/MODULE_71d6f1724eb9ca6bbf34+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1769f4ed8755d6b56ab33b3ba059b8f67b3f0dff5a098fc5ead75908c8dc238
3
+ size 3974144
neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+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_8d4a4e991c9ba3c051b5+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2947ac290d2cd5ee883a3ac6a70100840d60be5d3023a198925ee77c9659a5c9
3
+ size 647962
neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ede75e853a41a2fcd7eb69b4808a6532aca457b22ac06d93cdc82d6a6ef02d7
3
+ size 10650624
neuronxcc-2.17.194.0+d312836f/MODULE_8d4a4e991c9ba3c051b5+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e72eee1aada03be54345608adf36a2a14dd4a09e4ca74b0b4e1f43c48fd340
3
+ size 10788002
neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+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_bd7733fff1675159a47f+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d631073a722fad9a871e190a12264a286b62fa006a0db13e3e756ac27bce1ec
3
+ size 116998
neuronxcc-2.17.194.0+d312836f/MODULE_bd7733fff1675159a47f+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc313b6c628f4ba3273351a37c6894428d22d61a77d8c2ed36106df5577a5dec
3
+ size 3953664
neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+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_c7b34d5943a8e162e192+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7ffb9442cb991df71e1e421a445c3f85e51bce2cdd500ee8df9c57d9db2b12e
3
+ size 823706
neuronxcc-2.17.194.0+d312836f/MODULE_c7b34d5943a8e162e192+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be2105cf7b79efcc62310f75763d1554cebda64cfe44cfe0db6a762ac6f7c145
3
+ size 6237184
neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+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_ddd8df8ccbf7e2239d19+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c9cca486eab4d6045bf1d2ae56c02c9b7cc9027ce7807aec3a99b6ec062e26f
3
+ size 835006
neuronxcc-2.17.194.0+d312836f/MODULE_ddd8df8ccbf7e2239d19+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d80bc8aefb2c260e890a98ae4bd688260b3913b8225b5f70b5787c485c20ff4
3
+ size 6216704
neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+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_ded5e72f03277b22e294+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f1a89033c2a8421aa39547944cc7191df407797dc54e6bfd15d5ee70200f59
3
+ size 654848
neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b812fac2d4f21b8312ff2dd8fc25f6da0525f4bed3209d3a8d8d10b35fc9838b
3
+ size 10630144
neuronxcc-2.17.194.0+d312836f/MODULE_ded5e72f03277b22e294+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27e460c3f0013695f4aa064761eebeea5ced21cf6872e85e4b6efadd65ab196b
3
+ size 10767074
neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+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_fe2b7cb58538780206c1+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0ad82c036ff952e466d25b7dbdc6e161cc973bacf1b5d53307b6721234cf4b
3
+ size 641559
neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8e0c6b1706b368362e6dd65bbfcb2c60adefd26d0f746c243d4ae2f54198d64
3
+ size 10599424
neuronxcc-2.17.194.0+d312836f/MODULE_fe2b7cb58538780206c1+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba30b7dade65e54eff5ac251da714577a120d81992815ec050e202ba774513e
3
+ size 10719778
neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+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_fe86d2c41acff0457a14+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a395796e7fb4d2206523acf8855aeda9c769dcf30069f104221315aaf986b7c
3
+ size 135622
neuronxcc-2.17.194.0+d312836f/MODULE_fe86d2c41acff0457a14+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:150c86c1e993eeeffe85d8e7cb0c93b9e35702b4b6f13a775bc857b2410af352
3
+ size 3984384