Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
optimum-internal-testing-user commited on
Commit
ab74417
·
verified ·
1 Parent(s): c84dc63

Synchronizing local compiler cache.

Browse files
Files changed (33) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/d13007155871310e9d59.json +77 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/1936c94f4f4be8938bd0.json +71 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/8d1d4070dcdd08bae7ac.json +71 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.hlo_module.pb +1 -1
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.neff +1 -1
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/compile_flags.json +1 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.done +0 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.hlo_module.pb +3 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.neff +3 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/wrapped_neff.hlo +3 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/compile_flags.json +1 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/model.done +0 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/model.hlo_module.pb +3 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/model.neff +3 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/wrapped_neff.hlo +3 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/compile_flags.json +1 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/model.done +0 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/model.hlo_module.pb +3 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/model.neff +3 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/wrapped_neff.hlo +3 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/compile_flags.json +1 -0
  23. neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/model.done +0 -0
  24. neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/model.hlo_module.pb +3 -0
  25. neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/model.neff +3 -0
  26. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/compile_flags.json +1 -0
  27. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/model.done +0 -0
  28. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/model.hlo_module.pb +3 -0
  29. neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/model.neff +3 -0
  30. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/compile_flags.json +1 -0
  31. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.done +0 -0
  32. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.hlo_module.pb +3 -0
  33. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.neff +3 -0
.gitattributes CHANGED
@@ -3638,3 +3638,12 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_b75a1633e11cc79ab173+677eeb9d/model.neff f
3638
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3639
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3640
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
3638
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_cb6ef7b1205d1d19bf46+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3639
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_2aa08aa6793c444a88ea+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3640
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3641
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3642
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3643
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3644
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3645
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3646
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3647
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3648
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3649
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/d13007155871310e9d59.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": "2.19.8089.0+8ab9f450",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.3.0.dev4",
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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/1936c94f4f4be8938bd0.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": 4096,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 4096,
40
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev4",
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": 4096,
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-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/8d1d4070dcdd08bae7ac.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": "2.19.8089.0+8ab9f450",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev4",
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-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eed8bde27b8d98c1de6258bd7b7317e170b3457387b5cfe8fc69e2903b652c96
3
  size 567258
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c6fef5f43fa4c973d3883852fad45776b35c6ac54c8fd465e4ce7fd19312bf3
3
  size 567258
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1514adc3f2a36e3f52d0618eb23008d867908d4c2008aa8b997764f3cb7d5532
3
  size 1137664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c39af1026c38e0f1c6259af7eb51555806b532084441cf0f1724c22289a2c77f
3
  size 1137664
neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:205f1c271ab14351f6f4a1e4cc72990f3667414fa57ac67360d3d5cd685f6cb4
3
+ size 81748
neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a55519f7b433ed16d2bfb11a6a9f34f060590c7be7601d114fef7c611d3c6f7
3
+ size 615424
neuronxcc-2.19.8089.0+8ab9f450/MODULE_2e56c815cb8a782e4314+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39e436195b67d0ab588c8cf187d7153b133f9b757a7d318ff045b0148c924a15
3
+ size 623263
neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f303f276ce076fb6b2e0c9b889af51b3231dad571757a9b5403a2b8c5352fb
3
+ size 620149
neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4620324c133addb0923a54be50fd6d833007442671480b2ae0b7b80b56b2834b
3
+ size 1086464
neuronxcc-2.19.8089.0+8ab9f450/MODULE_599d6edc870558135559+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7f8136e1a592ab9c67913801939e1e65aace850a0da04adb483a212b349e552
3
+ size 1231490
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e67049c53baa01672a2d7a8149c8300eb62cf91e079a87f78063c3408ddd983
3
+ size 620149
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f99d023048b6a12bffa03922bb16d1f553fcd740f91cbce6da6eafb64073f348
3
+ size 1168384
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5c32a1f8ec7886c7acf5+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecaba4c0f07d8780efa467dd855f46b7fc6ad1c4ab467c8dcf6224c36f04231e
3
+ size 1313410
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edb31db519104a49dbf6e98ca066e2af4285bf29d3f6d350af6907c16516911
3
+ size 704974
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8f97b7ff93cba2da869a+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d5274c4bd4450f49f6edc97bb6b483a12ff1bfdc7cc3dd6179d2d31be4ea952
3
+ size 19631104
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+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-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e819dc05ecabfb98da77c8dfc10e04c1de711b67ec608d686399606542c95dd
3
+ size 149919
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a140491c564e6bf195f8+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34a0fc881707e20297ed8caf4c09ab4a7ee88ade6a13e99e53fa2a4100b18b2b
3
+ size 594944
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/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_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9399bc7fe9f7feea08c1cbedab9753ec7e2130a660287444411d897b123530f4
3
+ size 92962
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ab879d1cb66ac8ac1890+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1887e9cac34678f15e811d0d77ea06bfe438667fd8952aaca388a118a06a7d6
3
+ size 213668864