Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
Community
652
dacorvo HF Staff commited on
Commit
925ac54
·
verified ·
1 Parent(s): 0cdb0a5

Synchronizing local compiler cache.

Browse files
Files changed (42) hide show
  1. .gitattributes +13 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/c44eac5d03bacf7643a3782a45cab2feff584652bee95cd3c43c7d2600b2f3c5/47d55cf4c106b617b12b.json +63 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/c44eac5d03bacf7643a3782a45cab2feff584652bee95cd3c43c7d2600b2f3c5/7c0c03b622f70eb1983f.json +63 -0
  4. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/c44eac5d03bacf7643a3782a45cab2feff584652bee95cd3c43c7d2600b2f3c5/d0d11d951d16b0d6f98e.json +63 -0
  5. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/llama/unsloth/Meta-Llama-3.1-8B-Instruct/7c0c03b622f70eb1983f.json +63 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/compile_flags.json +1 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/model.done +0 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/model.hlo_module.pb +3 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/model.neff +3 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/wrapped_neff.hlo +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/compile_flags.json +1 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/model.done +0 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/model.hlo_module.pb +3 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/model.neff +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/compile_flags.json +1 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/model.done +0 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/model.hlo_module.pb +3 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/model.neff +3 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/compile_flags.json +1 -0
  20. neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/model.done +0 -0
  21. neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/model.hlo_module.pb +3 -0
  22. neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/model.neff +3 -0
  23. neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/wrapped_neff.hlo +3 -0
  24. neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/compile_flags.json +1 -0
  25. neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/model.done +0 -0
  26. neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/model.hlo_module.pb +3 -0
  27. neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/model.neff +3 -0
  28. neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/wrapped_neff.hlo +3 -0
  29. neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/compile_flags.json +1 -0
  30. neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/model.done +0 -0
  31. neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/model.hlo_module.pb +3 -0
  32. neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/model.neff +3 -0
  33. neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/wrapped_neff.hlo +3 -0
  34. neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/compile_flags.json +1 -0
  35. neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/model.done +0 -0
  36. neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/model.hlo_module.pb +3 -0
  37. neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/model.neff +3 -0
  38. neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/compile_flags.json +1 -0
  39. neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/model.done +0 -0
  40. neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/model.hlo_module.pb +3 -0
  41. neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/model.neff +3 -0
  42. neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -16642,3 +16642,16 @@ neuronxcc-2.21.33363.0+82129205/MODULE_f2730f4e10cea57ff5c9+09c69049/model.neff
16642
  neuronxcc-2.21.33363.0+82129205/MODULE_f2730f4e10cea57ff5c9+09c69049/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
16643
  neuronxcc-2.21.33363.0+82129205/MODULE_f95d75b645760c02ab07+fef23081/model.neff filter=lfs diff=lfs merge=lfs -text
16644
  neuronxcc-2.21.33363.0+82129205/MODULE_f95d75b645760c02ab07+fef23081/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
16642
  neuronxcc-2.21.33363.0+82129205/MODULE_f2730f4e10cea57ff5c9+09c69049/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
16643
  neuronxcc-2.21.33363.0+82129205/MODULE_f95d75b645760c02ab07+fef23081/model.neff filter=lfs diff=lfs merge=lfs -text
16644
  neuronxcc-2.21.33363.0+82129205/MODULE_f95d75b645760c02ab07+fef23081/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
16645
+ neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
16646
+ neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
16647
+ neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
16648
+ neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
16649
+ neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
16650
+ neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
16651
+ neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
16652
+ neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
16653
+ neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
16654
+ neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
16655
+ neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
16656
+ neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
16657
+ neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/c44eac5d03bacf7643a3782a45cab2feff584652bee95cd3c43c7d2600b2f3c5/47d55cf4c106b617b12b.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "neuron": {
20
+ "_serialized_key": "NxDNeuronConfig",
21
+ "batch_size": 1,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "a2856192dd7c25b842431f39c179a6c2c2f627d1",
25
+ "continuous_batching": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 4,
30
+ "max_batch_size": 1,
31
+ "max_context_length": 4096,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 4096,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.5",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 4
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 32,
48
+ "num_key_value_heads": 8,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 8.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": false,
60
+ "unsloth_fixed": true,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/c44eac5d03bacf7643a3782a45cab2feff584652bee95cd3c43c7d2600b2f3c5/7c0c03b622f70eb1983f.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "neuron": {
20
+ "_serialized_key": "NxDNeuronConfig",
21
+ "batch_size": 1,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "a2856192dd7c25b842431f39c179a6c2c2f627d1",
25
+ "continuous_batching": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 1,
31
+ "max_context_length": 4096,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 4096,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.5",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 32,
48
+ "num_key_value_heads": 8,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 8.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": false,
60
+ "unsloth_fixed": true,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/c44eac5d03bacf7643a3782a45cab2feff584652bee95cd3c43c7d2600b2f3c5/d0d11d951d16b0d6f98e.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "neuron": {
20
+ "_serialized_key": "NxDNeuronConfig",
21
+ "batch_size": 1,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "a2856192dd7c25b842431f39c179a6c2c2f627d1",
25
+ "continuous_batching": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 1,
30
+ "max_batch_size": 1,
31
+ "max_context_length": 4096,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 4096,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.5",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 1
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 32,
48
+ "num_key_value_heads": 8,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 8.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": false,
60
+ "unsloth_fixed": true,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5/llama/unsloth/Meta-Llama-3.1-8B-Instruct/7c0c03b622f70eb1983f.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "LlamaForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 4096,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 14336,
16
+ "max_position_embeddings": 131072,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "neuron": {
20
+ "_serialized_key": "NxDNeuronConfig",
21
+ "batch_size": 1,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Meta-Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "a2856192dd7c25b842431f39c179a6c2c2f627d1",
25
+ "continuous_batching": false,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 1,
31
+ "max_context_length": 4096,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 4096,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.5",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 32,
48
+ "num_key_value_heads": 8,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 8.0,
53
+ "high_freq_factor": 4.0,
54
+ "low_freq_factor": 1.0,
55
+ "original_max_position_embeddings": 8192,
56
+ "rope_type": "llama3"
57
+ },
58
+ "rope_theta": 500000.0,
59
+ "tie_word_embeddings": false,
60
+ "unsloth_fixed": true,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab7ca118556b1fee4504cd4b8230029bd9b22cc9665cfac4809247209bff4bf7
3
+ size 1886537
neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc945c46865a7ef4388c9a9c63860e388ee4b034fd97f261537ebc52174a13d5
3
+ size 6206464
neuronxcc-2.21.33363.0+82129205/MODULE_02256b8a2aab1d389750+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d48de984710ece3577a42a71b1d4d97c90c36d9a38f0281ff26e12e9098cf5f
3
+ size 6355736
neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf91372e5266a38116f8912356b3b74c412ffd2c98b6f44e4c26583f66561c27
3
+ size 1964972
neuronxcc-2.21.33363.0+82129205/MODULE_287b2eb93253738409b2+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df9d0290e7ebf02d82601ba64abd07e6003b2c1b336f9b3ea6ddc9f8229a750
3
+ size 220611584
neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985f7dcfefa9057f3dc39e009447320be2a88d8440ba9f733ab92c794bb84a3b
3
+ size 2109551
neuronxcc-2.21.33363.0+82129205/MODULE_48c6b59714f33f403b6c+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6cc1eef87d1fd4939a9a4147db9a0eab9e0dce91d67a7b8c7364e08fee22872
3
+ size 3431424
neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c9d705b0f12e0764e57837377fb398e92b4994ca9b3c331408060e010264771
3
+ size 2011291
neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3e20ffab9fee3b9d387638fdddb0dc0b9fb2bcd5b6da7c88afebfaaae31015
3
+ size 10650624
neuronxcc-2.21.33363.0+82129205/MODULE_554980bb5466318ce288+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efe457e68d79afd651012a8545dc27e273f9bb02878e8fce9d94b5f4df67c01a
3
+ size 10799895
neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28831f2874fbfc88eed29b0a4bf14fdc8613d7f0c64534dcec0ba92fc97dea36
3
+ size 1740702
neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4f63364f33b5c65a7e241ac86a943eb186de0fd4665450f0546e8c5a32aed79
3
+ size 18033664
neuronxcc-2.21.33363.0+82129205/MODULE_669f67001bdd818b57d9+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2bbab08141911d8f65a75d1df53bc234a5cfe63aaf849aabc465bb1654cf5e4
3
+ size 18184971
neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7ff5cc2aa0bc7230218b908ad415301d7a533adebc054dbb3bddff8acc95157
3
+ size 2011035
neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e14ffbc508d66814c11e2d5349871b8c52727a392c86b3bfab014d11de76ff2
3
+ size 10363904
neuronxcc-2.21.33363.0+82129205/MODULE_6d3a2f443a5dcad08e97+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f9c24cd1c4c6cff488ce489510de54da6c8a0749735c44fbbbfc77f9c5dcc9
3
+ size 10513175
neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3984ae61091c4443fdb4f995e79495c798890c4606c2d38ce505c04e6cd375d
3
+ size 2234801
neuronxcc-2.21.33363.0+82129205/MODULE_72f6735adcf8f2f6110e+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45ab56fcbe7e5e6e1c2818a789128d8e00b6299c7b9b6e7559a4c1d602845b9d
3
+ size 6441984
neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5a8ea445bd933d99e11a6c29be2587d9af783ca63b19fcac88011413435aaa9
3
+ size 1740446
neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b1e78219f08e3fe5da1929d79af0d534552e3d253c0fc4ca2a260394bbb2aa
3
+ size 17449984
neuronxcc-2.21.33363.0+82129205/MODULE_b89db8926870d0a7561c+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fbdd8a78fceef473d801bbbd2ca259b65d9e350527e686c545cca75c7786daf
3
+ size 17601291