Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files
xet
 Community
709
dacorvo HF Staff commited on
Commit
a47502b
·
verified ·
1 Parent(s): 23a38c7

Synchronizing local compiler cache.

Browse files
Files changed (23) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/5b525a985475816c688b.json +83 -0
  3. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/91cfcc11840e3c567b0b.json +64 -0
  4. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/91cfcc11840e3c567b0b.json +64 -0
  5. neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/Qwen/Qwen2.5-0.5B/5b525a985475816c688b.json +83 -0
  6. neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/compile_flags.json +1 -0
  7. neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/model.done +0 -0
  8. neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/model.hlo_module.pb +3 -0
  9. neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/model.neff +3 -0
  10. neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/wrapped_neff.hlo +3 -0
  11. neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/compile_flags.json +1 -0
  12. neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/model.done +0 -0
  13. neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/model.hlo_module.pb +3 -0
  14. neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/model.neff +3 -0
  15. neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/wrapped_neff.hlo +3 -0
  16. neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/compile_flags.json +1 -0
  17. neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/model.done +0 -0
  18. neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/model.hlo_module.pb +3 -0
  19. neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/model.neff +3 -0
  20. neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/compile_flags.json +1 -0
  21. neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/model.done +0 -0
  22. neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/model.hlo_module.pb +3 -0
  23. neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/model.neff +3 -0
.gitattributes CHANGED
@@ -17777,3 +17777,9 @@ neuronxcc-2.26.6360.0+6f180f47/MODULE_e55d82735fdae39dd63f+519f203d/model.neff f
17777
  neuronxcc-2.26.6360.0+6f180f47/MODULE_39a75826b85bdf893aef+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
17778
  neuronxcc-2.26.6360.0+6f180f47/MODULE_8f6f3d4df82b29f0bf1a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
17779
  neuronxcc-2.26.6360.0+6f180f47/MODULE_8f6f3d4df82b29f0bf1a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
17777
  neuronxcc-2.26.6360.0+6f180f47/MODULE_39a75826b85bdf893aef+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
17778
  neuronxcc-2.26.6360.0+6f180f47/MODULE_8f6f3d4df82b29f0bf1a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
17779
  neuronxcc-2.26.6360.0+6f180f47/MODULE_8f6f3d4df82b29f0bf1a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
17780
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
17781
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
17782
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
17783
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
17784
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
17785
+ neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/5b525a985475816c688b.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dtype": "bfloat16",
10
+ "hidden_act": "silu",
11
+ "hidden_size": 896,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4864,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention"
39
+ ],
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 24,
42
+ "model_type": "qwen2",
43
+ "neuron": {
44
+ "_serialized_key": "NxDNeuronConfig",
45
+ "batch_size": 2,
46
+ "capacity_factor": null,
47
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
48
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
49
+ "continuous_batching": true,
50
+ "ep_degree": 1,
51
+ "fused_qkv": false,
52
+ "glu_mlp": true,
53
+ "local_ranks_size": 2,
54
+ "max_batch_size": 2,
55
+ "max_context_length": 1024,
56
+ "max_topk": 256,
57
+ "n_active_tokens": 1024,
58
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
59
+ "on_device_sampling": false,
60
+ "optimum_neuron_version": "0.4.7.dev0",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "prefill_chunk_size": 0,
64
+ "sequence_length": 1024,
65
+ "speculation_length": 0,
66
+ "start_rank_id": 0,
67
+ "target": "trn1",
68
+ "torch_dtype": "bfloat16",
69
+ "tp_degree": 2
70
+ },
71
+ "num_attention_heads": 14,
72
+ "num_hidden_layers": 24,
73
+ "num_key_value_heads": 2,
74
+ "rms_norm_eps": 1e-06,
75
+ "rope_scaling": null,
76
+ "rope_theta": 1000000.0,
77
+ "sliding_window": null,
78
+ "tie_word_embeddings": true,
79
+ "use_cache": true,
80
+ "use_mrope": false,
81
+ "use_sliding_window": false,
82
+ "vocab_size": 151936
83
+ }
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/91cfcc11840e3c567b0b.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Llama-3.2-1B-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": 64,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
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/Llama-3.2-1B-Instruct",
24
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
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": "2.26.6360.0+6f180f47",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.7.dev0",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_chunk_size": 1024,
40
+ "sequence_length": 4096,
41
+ "speculation_length": 0,
42
+ "start_rank_id": 0,
43
+ "target": "trn1",
44
+ "torch_dtype": "bfloat16",
45
+ "tp_degree": 2
46
+ },
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 32.0,
54
+ "high_freq_factor": 4.0,
55
+ "low_freq_factor": 1.0,
56
+ "original_max_position_embeddings": 8192,
57
+ "rope_type": "llama3"
58
+ },
59
+ "rope_theta": 500000.0,
60
+ "tie_word_embeddings": true,
61
+ "unsloth_fixed": true,
62
+ "use_cache": true,
63
+ "vocab_size": 128256
64
+ }
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/llama/unsloth/Llama-3.2-1B-Instruct/91cfcc11840e3c567b0b.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "unsloth/Llama-3.2-1B-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": 64,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2048,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 8192,
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/Llama-3.2-1B-Instruct",
24
+ "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
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": "2.26.6360.0+6f180f47",
35
+ "on_device_sampling": true,
36
+ "optimum_neuron_version": "0.4.7.dev0",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_chunk_size": 1024,
40
+ "sequence_length": 4096,
41
+ "speculation_length": 0,
42
+ "start_rank_id": 0,
43
+ "target": "trn1",
44
+ "torch_dtype": "bfloat16",
45
+ "tp_degree": 2
46
+ },
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 16,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 32.0,
54
+ "high_freq_factor": 4.0,
55
+ "low_freq_factor": 1.0,
56
+ "original_max_position_embeddings": 8192,
57
+ "rope_type": "llama3"
58
+ },
59
+ "rope_theta": 500000.0,
60
+ "tie_word_embeddings": true,
61
+ "unsloth_fixed": true,
62
+ "use_cache": true,
63
+ "vocab_size": 128256
64
+ }
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7.dev0/qwen2/Qwen/Qwen2.5-0.5B/5b525a985475816c688b.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "dtype": "bfloat16",
10
+ "hidden_act": "silu",
11
+ "hidden_size": 896,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4864,
14
+ "layer_types": [
15
+ "full_attention",
16
+ "full_attention",
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention"
39
+ ],
40
+ "max_position_embeddings": 32768,
41
+ "max_window_layers": 24,
42
+ "model_type": "qwen2",
43
+ "neuron": {
44
+ "_serialized_key": "NxDNeuronConfig",
45
+ "batch_size": 2,
46
+ "capacity_factor": null,
47
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
48
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
49
+ "continuous_batching": true,
50
+ "ep_degree": 1,
51
+ "fused_qkv": false,
52
+ "glu_mlp": true,
53
+ "local_ranks_size": 2,
54
+ "max_batch_size": 2,
55
+ "max_context_length": 1024,
56
+ "max_topk": 256,
57
+ "n_active_tokens": 1024,
58
+ "neuronxcc_version": "2.26.6360.0+6f180f47",
59
+ "on_device_sampling": false,
60
+ "optimum_neuron_version": "0.4.7.dev0",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "prefill_chunk_size": 0,
64
+ "sequence_length": 1024,
65
+ "speculation_length": 0,
66
+ "start_rank_id": 0,
67
+ "target": "trn1",
68
+ "torch_dtype": "bfloat16",
69
+ "tp_degree": 2
70
+ },
71
+ "num_attention_heads": 14,
72
+ "num_hidden_layers": 24,
73
+ "num_key_value_heads": 2,
74
+ "rms_norm_eps": 1e-06,
75
+ "rope_scaling": null,
76
+ "rope_theta": 1000000.0,
77
+ "sliding_window": null,
78
+ "tie_word_embeddings": true,
79
+ "use_cache": true,
80
+ "use_mrope": false,
81
+ "use_sliding_window": false,
82
+ "vocab_size": 151936
83
+ }
neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aabfba0836e862e159fb7556f780dce5871ce41313c64a1844d2257d5523e019
3
+ size 2534920
neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55feb3b6a7ce6908a883038abcae65753b3508d626f00710cf22f3007802101e
3
+ size 1608704
neuronxcc-2.26.6360.0+6f180f47/MODULE_2477fa968f55f9199f8a+84337dd9/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3fa12535e9167b251fac74056b454eca418a2f7aa5ee02e5ac938f86a4e6a145
3
+ size 1764895
neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/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", "--verbose=35", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b00f28867223bfad558c0c1202de9f21a7713400885c0e3de455effc1740df8
3
+ size 1703387
neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b1722d8621d045b4c08973b679276c02da22953b18c5f0be15aa8f93176b20f
3
+ size 2018304
neuronxcc-2.26.6360.0+6f180f47/MODULE_63ff8a20a88a4bac2002+84337dd9/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b832e838f1e774d77e5caf71dd3d0e59d97dcbed42dbd2898c683f161b225fa0
3
+ size 2092388
neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/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", "--verbose=35", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f93e284b93ca29fe705f55ee041438254c7d18aafad5d6bc05276f19bc1eb5d
3
+ size 2315698
neuronxcc-2.26.6360.0+6f180f47/MODULE_6eb01665cf75ca34fde7+519f203d/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15d9b6da1e6b37387e0b998c7ea89186854f2a1d3bcaf174d54cdb0e161d347b
3
+ size 3410944
neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/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", "--verbose=35", "--logfile=/tmp/nxd_model/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/model.done ADDED
File without changes
neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5332bca0abb87d41b67a17d9eefb4640f576401116498af9681ecf9f1362e721
3
+ size 2191191
neuronxcc-2.26.6360.0+6f180f47/MODULE_f0727109886547b51ba5+12dd9119/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ee1c4fcaec1ef4d4a3cb3615defc40a98c529eb19cdbd5e245c60636dc1f553
3
+ size 12616704