Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
optimum-internal-testing-user commited on
Commit
7a4a969
·
verified ·
1 Parent(s): 6602d8e

Synchronizing local compiler cache.

Browse files
Files changed (32) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/db93285c05cc82b582ee.json +77 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/Qwen/Qwen2.5-0.5B/6bacc96516ec21c33b00.json +71 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/Qwen/Qwen2.5-0.5B/70edb03e45d1c6c15d62.json +71 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_1222f947950b01f3f12f+ed72d204/compile_flags.json +1 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_1222f947950b01f3f12f+ed72d204/model.done +0 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_1222f947950b01f3f12f+ed72d204/model.hlo_module.pb +3 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_1222f947950b01f3f12f+ed72d204/model.neff +3 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/compile_flags.json +1 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.done +0 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.hlo_module.pb +3 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.neff +3 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+ed72d204/compile_flags.json +1 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+ed72d204/model.done +0 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+ed72d204/model.hlo_module.pb +3 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+ed72d204/model.neff +3 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/compile_flags.json +1 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/model.done +0 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/model.hlo_module.pb +3 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/model.neff +3 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/wrapped_neff.hlo +3 -0
  22. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/compile_flags.json +1 -0
  23. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.done +0 -0
  24. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.hlo_module.pb +3 -0
  25. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.neff +3 -0
  26. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/wrapped_neff.hlo +3 -0
  27. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/compile_flags.json +1 -0
  28. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/model.done +0 -0
  29. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/model.hlo_module.pb +3 -0
  30. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/model.neff +3 -0
  31. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/wrapped_neff.hlo +3 -0
  32. neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff +1 -1
.gitattributes CHANGED
@@ -3562,3 +3562,12 @@ neuronxcc-2.17.194.0+d312836f/MODULE_a642e4644f4dd00e7e7c+bfe5714b/model.neff fi
3562
  neuronxcc-2.17.194.0+d312836f/MODULE_bde59c9c06380a392ee9+841d78e1/model.neff filter=lfs diff=lfs merge=lfs -text
3563
  neuronxcc-2.17.194.0+d312836f/MODULE_a243c4209ea1fb29f89e+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3564
  neuronxcc-2.17.194.0+d312836f/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
3562
  neuronxcc-2.17.194.0+d312836f/MODULE_bde59c9c06380a392ee9+841d78e1/model.neff filter=lfs diff=lfs merge=lfs -text
3563
  neuronxcc-2.17.194.0+d312836f/MODULE_a243c4209ea1fb29f89e+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3564
  neuronxcc-2.17.194.0+d312836f/MODULE_d3a9fa4c26a43f9f624a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3565
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1222f947950b01f3f12f+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3566
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3567
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
3568
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3569
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3570
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3571
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3572
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
3573
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev3/llama/llamafactory/tiny-random-Llama-3/db93285c05cc82b582ee.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.dev3",
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.dev3/qwen2/Qwen/Qwen2.5-0.5B/6bacc96516ec21c33b00.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.dev3",
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+8ab9f450/0_REGISTRY/0.3.0.dev3/qwen2/Qwen/Qwen2.5-0.5B/70edb03e45d1c6c15d62.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.dev3",
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/MODULE_1222f947950b01f3f12f+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_1222f947950b01f3f12f+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1222f947950b01f3f12f+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8359875bdce3ee41bf5174cc06f5e649e933feac79dc4b3b28496b65cef619b
3
+ size 701615
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1222f947950b01f3f12f+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec544eb59c41b3a5ca119756ba0d7c7a4bd049a1cb116a3e153b0238fb3cb22
3
+ size 19631104
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+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_23bbc81be5a6f07d940c+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed8bde27b8d98c1de6258bd7b7317e170b3457387b5cfe8fc69e2903b652c96
3
+ size 567258
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23bbc81be5a6f07d940c+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1514adc3f2a36e3f52d0618eb23008d867908d4c2008aa8b997764f3cb7d5532
3
+ size 1137664
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+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_89320e29fb9683fe5b07+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40cac005f31149d93bb825bb8f1fe0d2febe6b59d2c904442d78cd339cc744a4
3
+ size 92682
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89320e29fb9683fe5b07+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9042fbe831ef84f8b6e8b9e02ad6213421259630b5d426121a7e2a741ee56e
3
+ size 213668864
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+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_9d3d853143a54d3b6fa6+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0459c9242d2a6cff842c70cb6e847a47bb7524117150a0b4eaacae2e7f46732f
3
+ size 613479
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47fc3474b36fe61a63a13defb04dc034511da1b9dbe3f9329a35f73b4110c3d5
3
+ size 1168384
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d3d853143a54d3b6fa6+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cad049f93b083ff44b99399191eb5cd18b6997de260ea9ba9843f698a02b31e
3
+ size 1313410
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+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_9d6472a07252b0ce1b30+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b1fc0df5d72d2bf09561d3762172af840ee9d87204f82ec8eb125258a3366af
3
+ size 81196
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01a963cd7ad2844c9fc8e5d88d5c77ede31b86c3064815307dfad2b370916a8b
3
+ size 615424
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:320b79be3b9147fad38deff107dee575748a9acb60df85398f2f7812d54573e3
3
+ size 623263
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+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_9df5787b5ac6aa6f2003+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3dc5884bbad043d149a0439dc8c022afaf39efa8a0d539f1e7c41b77570aa7f
3
+ size 613479
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d3ce222dbc13d7cb62e8070ad9748061247fe55626d6782856568a11366b1a
3
+ size 1086464
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:714de6ff44a76409405df1b821141a32925d1c00daeb394dd2aceb7dab8ee118
3
+ size 1231490
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:988562484e328103e6a1144382a2e1f2406ee43963f03bcc068879224acb1cab
3
  size 594944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c65e288385815e30931e7f53778f12cbbc3d58993a900e7d77323fff681a052
3
  size 594944