Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
dacorvo HF Staff commited on
Commit
57ad2dc
·
verified ·
1 Parent(s): fbee861

Synchronizing local compiler cache.

Browse files
Files changed (35) hide show
  1. .gitattributes +11 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/ec2b5e8bc22f267c16fe.json +77 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/184ac9147c5c3a01108b.json +71 -0
  4. neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+bfe5714b/compile_flags.json +1 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+bfe5714b/model.done +0 -0
  6. neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+bfe5714b/model.hlo_module.pb +3 -0
  7. neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+bfe5714b/model.neff +3 -0
  8. neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+bfe5714b/compile_flags.json +1 -0
  9. neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+bfe5714b/model.done +0 -0
  10. neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+bfe5714b/model.hlo_module.pb +3 -0
  11. neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+bfe5714b/model.neff +3 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+bfe5714b/compile_flags.json +1 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+bfe5714b/model.done +0 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+bfe5714b/model.hlo_module.pb +3 -0
  15. neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+bfe5714b/model.neff +3 -0
  16. neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/compile_flags.json +1 -0
  17. neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/model.done +0 -0
  18. neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/model.hlo_module.pb +3 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/model.neff +3 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/wrapped_neff.hlo +3 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/compile_flags.json +1 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/model.done +0 -0
  23. neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/model.hlo_module.pb +3 -0
  24. neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/model.neff +3 -0
  25. neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/wrapped_neff.hlo +3 -0
  26. neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/compile_flags.json +1 -0
  27. neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/model.done +0 -0
  28. neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/model.hlo_module.pb +3 -0
  29. neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/model.neff +3 -0
  30. neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/wrapped_neff.hlo +3 -0
  31. neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/compile_flags.json +1 -0
  32. neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/model.done +0 -0
  33. neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/model.hlo_module.pb +3 -0
  34. neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/model.neff +3 -0
  35. neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -3116,3 +3116,14 @@ neuronxcc-2.17.194.0+d312836f/MODULE_fc12e674baf93fa7e151+bfe5714b/model.neff fi
3116
  neuronxcc-2.17.194.0+d312836f/MODULE_72055a9b8fe0e4cf6282+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3117
  neuronxcc-2.17.194.0+d312836f/MODULE_72055a9b8fe0e4cf6282+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3118
  neuronxcc-2.17.194.0+d312836f/MODULE_b0335000c191d09c6572+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
3116
  neuronxcc-2.17.194.0+d312836f/MODULE_72055a9b8fe0e4cf6282+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3117
  neuronxcc-2.17.194.0+d312836f/MODULE_72055a9b8fe0e4cf6282+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3118
  neuronxcc-2.17.194.0+d312836f/MODULE_b0335000c191d09c6572+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3119
+ neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3120
+ neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3121
+ neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3122
+ neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3123
+ neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3124
+ neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3125
+ neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3126
+ neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3127
+ neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3128
+ neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3129
+ neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/llama/llamafactory/tiny-random-Llama-3/ec2b5e8bc22f267c16fe.json ADDED
@@ -0,0 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "llamafactory/tiny-random-Llama-3",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "head_dim": 4,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 16,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 64,
15
+ "max_position_embeddings": 131072,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "neuron": {
19
+ "_serialized_key": "NxDNeuronConfig",
20
+ "async_mode": false,
21
+ "attn_kernel_enabled": false,
22
+ "batch_size": 1,
23
+ "capacity_factor": null,
24
+ "cc_pipeline_tiling_factor": 2,
25
+ "checkpoint_id": "llamafactory/tiny-random-Llama-3",
26
+ "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
27
+ "continuous_batching": false,
28
+ "enable_bucketing": false,
29
+ "ep_degree": 1,
30
+ "flash_decoding_enabled": false,
31
+ "fused_qkv": true,
32
+ "glu_mlp": true,
33
+ "is_chunked_prefill": false,
34
+ "local_ranks_size": 2,
35
+ "logical_nc_config": 1,
36
+ "max_batch_size": 1,
37
+ "max_context_length": 131072,
38
+ "max_topk": 256,
39
+ "mlp_kernel_enabled": false,
40
+ "mlp_kernel_fuse_residual_add": false,
41
+ "n_active_tokens": 131072,
42
+ "neuronxcc_version": "2.17.194.0+d312836f",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.3.0.dev2",
46
+ "output_logits": false,
47
+ "padding_side": "right",
48
+ "pp_degree": 1,
49
+ "qk_layernorm": false,
50
+ "qkv_kernel_enabled": false,
51
+ "rpl_reduce_dtype": "bfloat16",
52
+ "sequence_length": 131072,
53
+ "sequence_parallel_enabled": false,
54
+ "speculation_length": 0,
55
+ "start_rank_id": 0,
56
+ "target": null,
57
+ "torch_dtype": "bfloat16",
58
+ "tp_degree": 2,
59
+ "vocab_parallel": false
60
+ },
61
+ "num_attention_heads": 4,
62
+ "num_hidden_layers": 2,
63
+ "num_key_value_heads": 4,
64
+ "pretraining_tp": 1,
65
+ "rms_norm_eps": 1e-05,
66
+ "rope_scaling": {
67
+ "factor": 8.0,
68
+ "high_freq_factor": 4.0,
69
+ "low_freq_factor": 1.0,
70
+ "original_max_position_embeddings": 8192,
71
+ "rope_type": "llama3"
72
+ },
73
+ "rope_theta": 500000.0,
74
+ "tie_word_embeddings": false,
75
+ "use_cache": true,
76
+ "vocab_size": 128256
77
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/qwen2/Qwen/Qwen2.5-0.5B/184ac9147c5c3a01108b.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-0.5B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 896,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 4864,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 24,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 1,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
24
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
25
+ "continuous_batching": false,
26
+ "enable_bucketing": false,
27
+ "ep_degree": 1,
28
+ "flash_decoding_enabled": false,
29
+ "fused_qkv": false,
30
+ "glu_mlp": true,
31
+ "is_chunked_prefill": false,
32
+ "local_ranks_size": 2,
33
+ "logical_nc_config": 1,
34
+ "max_batch_size": 1,
35
+ "max_context_length": 128,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 128,
40
+ "neuronxcc_version": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev2",
44
+ "output_logits": false,
45
+ "padding_side": "right",
46
+ "pp_degree": 1,
47
+ "qk_layernorm": false,
48
+ "qkv_kernel_enabled": false,
49
+ "rpl_reduce_dtype": "bfloat16",
50
+ "sequence_length": 128,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "bfloat16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 14,
60
+ "num_hidden_layers": 24,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000.0,
65
+ "sliding_window": 32768,
66
+ "tie_word_embeddings": true,
67
+ "use_cache": true,
68
+ "use_mrope": false,
69
+ "use_sliding_window": false,
70
+ "vocab_size": 151936
71
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+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_12343f539f64e8427d30+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1289a2c559df7c88f73d3c8226a619c96ef2625ca170e14352c3afcbd373f7
3
+ size 163488
neuronxcc-2.17.194.0+d312836f/MODULE_12343f539f64e8427d30+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a7a8b0bd716df3ff6b7191cdd5a90a1ffc2ab74577b2f2cfd80d003a8a98c2
3
+ size 213853184
neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+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_2305ba70fd0a2832ceca+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40b3c4817ffe70e83920707fc0d6ffc7239e7d0c177dde1e8471140aa5e06d71
3
+ size 163488
neuronxcc-2.17.194.0+d312836f/MODULE_2305ba70fd0a2832ceca+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3329c1312200c8e16a2c3db39263f73ea972faf42bf67e01cae053bc5e3beca
3
+ size 213853184
neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+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_506394735e22714a6fbc+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dd89891855efbf46d77661bc94ffa5c299634698c6b824b61b5c8760a06785c
3
+ size 1214876
neuronxcc-2.17.194.0+d312836f/MODULE_506394735e22714a6fbc+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:167deb75f8fa57846d3f92d9eaf136b80fe3a20586b0b464d036f126dd44389e
3
+ size 1168384
neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+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_a4ec5c639ea6c2922365+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f210b752780a23e9743882446a5bd9f555bd0d3acd713f29fd06b95a12fcb91e
3
+ size 175310
neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58ab02def7be45d4f1f3c72e2411b2e5f00c2d5be315342a6c055b6ea6479a13
3
+ size 472064
neuronxcc-2.17.194.0+d312836f/MODULE_a4ec5c639ea6c2922365+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d106cc6e7f4e1503e56906e88f89a5c8859e45cd1ca07ffbc3ed85c2c2495ab8
3
+ size 479903
neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+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_b254587b1ec9eec17e0e+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9635c56bb978143c80956f7a34fc573314117fc043d3747a51693ac32078aa58
3
+ size 576230
neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcde9f0c96ab2eb517b4adcbe4e86f7350e6791d925d82d673683ba0ca0e1523
3
+ size 1455104
neuronxcc-2.17.194.0+d312836f/MODULE_b254587b1ec9eec17e0e+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7384d249ffdd8b33de3231856ef834e137bccdc3336bbaeb080d91b858186f7
3
+ size 1600015
neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+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_c0cc3ee540cc1113e295+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b636c76487a38551ebdb96f01c35cbf5ccca76d407743191522afb4023a8ef7a
3
+ size 175310
neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b953c46d63d9118f70279743f7d72f4673b0e2ac760304be3d3177ae4e26ffc
3
+ size 472064
neuronxcc-2.17.194.0+d312836f/MODULE_c0cc3ee540cc1113e295+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24b725ce94e4ab1b3e001c1c315346f3abc0ba8e68607f08eeea02c093bfed02
3
+ size 479903
neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+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_ec98086d86f184f276f1+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3fd4246fa1794c96c88427b3948545c9ed616b03b550783b3eefdb580b6419
3
+ size 1529642
neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46bdcbe69adfd86c08d08a23cd6c4dac03501cd3267968d4ac4344d2c1fd6672
3
+ size 1127424
neuronxcc-2.17.194.0+d312836f/MODULE_ec98086d86f184f276f1+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cacbbbe1d2bca4aa110cd777cff0f36276d2fdf6e09657c6c072a10157df7cd4
3
+ size 1272450