Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
dacorvo HF Staff commited on
Commit
1d41b70
·
verified ·
1 Parent(s): 22e42b9

Synchronizing local compiler cache.

Browse files
Files changed (32) hide show
  1. .gitattributes +5 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/2889709d0ef08af4f95e.json +65 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/543a9be1442087763767.json +65 -0
  4. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/ad754c745489e1bcbff4.json +65 -0
  5. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/ae28137286c4dec3bd52.json +65 -0
  6. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/c5610aa8599c59407f39.json +65 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/compile_flags.json +1 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/model.done +0 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/model.hlo_module.pb +3 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/model.neff +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/compile_flags.json +1 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/model.done +0 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/model.hlo_module.pb +3 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/model.neff +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_6007347d914257cec196+24129607/model.hlo_module.pb +1 -1
  16. neuronxcc-2.21.33363.0+82129205/MODULE_6007347d914257cec196+24129607/model.neff +1 -1
  17. neuronxcc-2.21.33363.0+82129205/MODULE_782036f3eac1b6db6d1b+a02c3a36/model.neff +1 -1
  18. neuronxcc-2.21.33363.0+82129205/MODULE_782036f3eac1b6db6d1b+a02c3a36/wrapped_neff.hlo +1 -1
  19. neuronxcc-2.21.33363.0+82129205/MODULE_84fd59187fd6be117f3a+fb4cc044/model.hlo_module.pb +1 -1
  20. neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/compile_flags.json +1 -0
  21. neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/model.done +0 -0
  22. neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/model.hlo_module.pb +3 -0
  23. neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/model.neff +3 -0
  24. neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/wrapped_neff.hlo +3 -0
  25. neuronxcc-2.21.33363.0+82129205/MODULE_cae8a0ee9677f6f7b542+6170d8e1/model.neff +1 -1
  26. neuronxcc-2.21.33363.0+82129205/MODULE_ce7e2a2399f408878a1f+24129607/model.neff +1 -1
  27. neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/compile_flags.json +1 -0
  28. neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/model.done +0 -0
  29. neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/model.hlo_module.pb +3 -0
  30. neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/model.neff +3 -0
  31. neuronxcc-2.21.33363.0+82129205/MODULE_f9b5b25ceb35d0bb7f65+a02c3a36/model.neff +1 -1
  32. neuronxcc-2.21.33363.0+82129205/MODULE_f9b5b25ceb35d0bb7f65+a02c3a36/wrapped_neff.hlo +1 -1
.gitattributes CHANGED
@@ -6941,3 +6941,8 @@ neuronxcc-2.21.33363.0+82129205/MODULE_f7c33365fd20ecd5bf1d+a02c3a36/model.neff
6941
  neuronxcc-2.21.33363.0+82129205/MODULE_f7c33365fd20ecd5bf1d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6942
  neuronxcc-2.21.33363.0+82129205/MODULE_ad16674dd3fc5a51c226+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6943
  neuronxcc-2.21.33363.0+82129205/MODULE_ad16674dd3fc5a51c226+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
6941
  neuronxcc-2.21.33363.0+82129205/MODULE_f7c33365fd20ecd5bf1d+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6942
  neuronxcc-2.21.33363.0+82129205/MODULE_ad16674dd3fc5a51c226+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6943
  neuronxcc-2.21.33363.0+82129205/MODULE_ad16674dd3fc5a51c226+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6944
+ neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6945
+ neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
6946
+ neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6947
+ neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6948
+ neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/2889709d0ef08af4f95e.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
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": 512,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 512,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": false,
36
+ "optimum_neuron_version": "0.4.6.dev1",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_batch_size": null,
40
+ "prefill_chunk_size": 64,
41
+ "sequence_length": 512,
42
+ "speculation_length": 0,
43
+ "start_rank_id": 0,
44
+ "target": "trn1",
45
+ "torch_dtype": "bfloat16",
46
+ "tp_degree": 2
47
+ },
48
+ "num_attention_heads": 32,
49
+ "num_hidden_layers": 16,
50
+ "num_key_value_heads": 8,
51
+ "pretraining_tp": 1,
52
+ "rms_norm_eps": 1e-05,
53
+ "rope_scaling": {
54
+ "factor": 32.0,
55
+ "high_freq_factor": 4.0,
56
+ "low_freq_factor": 1.0,
57
+ "original_max_position_embeddings": 8192,
58
+ "rope_type": "llama3"
59
+ },
60
+ "rope_theta": 500000.0,
61
+ "tie_word_embeddings": true,
62
+ "unsloth_fixed": true,
63
+ "use_cache": true,
64
+ "vocab_size": 128256
65
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/543a9be1442087763767.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
24
+ "checkpoint_revision": null,
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": 4,
31
+ "max_context_length": 512,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 512,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": false,
36
+ "optimum_neuron_version": "0.4.6.dev1",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_batch_size": null,
40
+ "prefill_chunk_size": 0,
41
+ "sequence_length": 512,
42
+ "speculation_length": 0,
43
+ "start_rank_id": 0,
44
+ "target": "trn1",
45
+ "torch_dtype": "bfloat16",
46
+ "tp_degree": 2
47
+ },
48
+ "num_attention_heads": 32,
49
+ "num_hidden_layers": 16,
50
+ "num_key_value_heads": 8,
51
+ "pretraining_tp": 1,
52
+ "rms_norm_eps": 1e-05,
53
+ "rope_scaling": {
54
+ "factor": 32.0,
55
+ "high_freq_factor": 4.0,
56
+ "low_freq_factor": 1.0,
57
+ "original_max_position_embeddings": 8192,
58
+ "rope_type": "llama3"
59
+ },
60
+ "rope_theta": 500000.0,
61
+ "tie_word_embeddings": true,
62
+ "unsloth_fixed": true,
63
+ "use_cache": true,
64
+ "vocab_size": 128256
65
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/ad754c745489e1bcbff4.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 2,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
24
+ "checkpoint_revision": null,
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": 2,
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": false,
36
+ "optimum_neuron_version": "0.4.6.dev1",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_batch_size": null,
40
+ "prefill_chunk_size": 0,
41
+ "sequence_length": 4096,
42
+ "speculation_length": 0,
43
+ "start_rank_id": 0,
44
+ "target": "trn1",
45
+ "torch_dtype": "bfloat16",
46
+ "tp_degree": 2
47
+ },
48
+ "num_attention_heads": 32,
49
+ "num_hidden_layers": 16,
50
+ "num_key_value_heads": 8,
51
+ "pretraining_tp": 1,
52
+ "rms_norm_eps": 1e-05,
53
+ "rope_scaling": {
54
+ "factor": 32.0,
55
+ "high_freq_factor": 4.0,
56
+ "low_freq_factor": 1.0,
57
+ "original_max_position_embeddings": 8192,
58
+ "rope_type": "llama3"
59
+ },
60
+ "rope_theta": 500000.0,
61
+ "tie_word_embeddings": true,
62
+ "unsloth_fixed": true,
63
+ "use_cache": true,
64
+ "vocab_size": 128256
65
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/ae28137286c4dec3bd52.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 4,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
24
+ "checkpoint_revision": null,
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": 4,
31
+ "max_context_length": 512,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 512,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": false,
36
+ "optimum_neuron_version": "0.4.6.dev1",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_batch_size": null,
40
+ "prefill_chunk_size": 256,
41
+ "sequence_length": 512,
42
+ "speculation_length": 0,
43
+ "start_rank_id": 0,
44
+ "target": "trn1",
45
+ "torch_dtype": "bfloat16",
46
+ "tp_degree": 2
47
+ },
48
+ "num_attention_heads": 32,
49
+ "num_hidden_layers": 16,
50
+ "num_key_value_heads": 8,
51
+ "pretraining_tp": 1,
52
+ "rms_norm_eps": 1e-05,
53
+ "rope_scaling": {
54
+ "factor": 32.0,
55
+ "high_freq_factor": 4.0,
56
+ "low_freq_factor": 1.0,
57
+ "original_max_position_embeddings": 8192,
58
+ "rope_type": "llama3"
59
+ },
60
+ "rope_theta": 500000.0,
61
+ "tie_word_embeddings": true,
62
+ "unsloth_fixed": true,
63
+ "use_cache": true,
64
+ "vocab_size": 128256
65
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev1/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/c5610aa8599c59407f39.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": null,
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": 512,
32
+ "max_topk": 256,
33
+ "n_active_tokens": 512,
34
+ "neuronxcc_version": "2.21.33363.0+82129205",
35
+ "on_device_sampling": false,
36
+ "optimum_neuron_version": "0.4.6.dev1",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "prefill_batch_size": null,
40
+ "prefill_chunk_size": 0,
41
+ "sequence_length": 512,
42
+ "speculation_length": 0,
43
+ "start_rank_id": 0,
44
+ "target": "trn1",
45
+ "torch_dtype": "bfloat16",
46
+ "tp_degree": 2
47
+ },
48
+ "num_attention_heads": 32,
49
+ "num_hidden_layers": 16,
50
+ "num_key_value_heads": 8,
51
+ "pretraining_tp": 1,
52
+ "rms_norm_eps": 1e-05,
53
+ "rope_scaling": {
54
+ "factor": 32.0,
55
+ "high_freq_factor": 4.0,
56
+ "low_freq_factor": 1.0,
57
+ "original_max_position_embeddings": 8192,
58
+ "rope_type": "llama3"
59
+ },
60
+ "rope_theta": 500000.0,
61
+ "tie_word_embeddings": true,
62
+ "unsloth_fixed": true,
63
+ "use_cache": true,
64
+ "vocab_size": 128256
65
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/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/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:581e0c38313f793e454f6b54dfb1ecb1d656c99c0d209e9d64889b1d9a55b75e
3
+ size 337832
neuronxcc-2.21.33363.0+82129205/MODULE_0cfed7877a9dd5b8b7c7+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:125d9c1b39317a00f748605fb0115910cb3530ec592f88449a0f51994c5dbc61
3
+ size 9882624
neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62798501073910892d94c408db95a1938f2ccab0eb9cc5d7c642247433e75494
3
+ size 471137
neuronxcc-2.21.33363.0+82129205/MODULE_5576f18429a0c403c1a8+6170d8e1/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd26e176593795e3fe97c4c9a0a390757bfcb561fb70cfae580dd6c7b5de9c5e
3
+ size 2049024
neuronxcc-2.21.33363.0+82129205/MODULE_6007347d914257cec196+24129607/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22b20c5cd4edf89b48829ae2e0e4ba8863c45c633664e744543ec1867f74f9c5
3
  size 435061
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8e19259e1f11b34e91536e9de4c84d84994a4c886e057e84d41c0987bb94584
3
  size 435061
neuronxcc-2.21.33363.0+82129205/MODULE_6007347d914257cec196+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e76d386e4211d647845f98e0b30e1a8444dbef3971a63444cf441e50fe42663f
3
  size 85750784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb2deac4f867d19e11a1bf5aff36c5bd8f16282a013712f52453f115167b5f20
3
  size 85750784
neuronxcc-2.21.33363.0+82129205/MODULE_782036f3eac1b6db6d1b+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f67609dcb979de7f4344f80d47f408c449f3fc0daa4761f7e0e98d441965bff7
3
  size 1741824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d4328ccc260649ebc72e8e4de1b77da8ebb2d91da591bd2532e2c3dbbacf687
3
  size 1741824
neuronxcc-2.21.33363.0+82129205/MODULE_782036f3eac1b6db6d1b+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a65cf109c5429e55ca0f30dc373c9fbb4be8126bec97f00e17120d0d694045b0
3
  size 1815793
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b27361020bc8d5ed27320a7c17463fc994418088ee83d25efd9842b36f75c4b
3
  size 1815793
neuronxcc-2.21.33363.0+82129205/MODULE_84fd59187fd6be117f3a+fb4cc044/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a0be6d1ceb8c9002241395262d7825ea7c83da19ad6ff21ef6cb3f18d3c0d2b
3
  size 573205
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:128abaed1aadd52fd9f95f287daf5aaf3dfe175895448c0aaaa437b83a0d30de
3
  size 573205
neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157bebc3b3b5bc17dac647520bc1e25d5d80d943248616fb1f2c8fc0d9f341b5
3
+ size 385563
neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:000150cc9e312caa862008b0add221972355123dfc3d24d442e4a625556478b3
3
+ size 2049024
neuronxcc-2.21.33363.0+82129205/MODULE_89fc2ce00488bb7d71aa+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8618cd779c7f7a28dbdd9c338fd5a4040c7b4bbe2ef718f159d5b7cee401a6de
3
+ size 2123007
neuronxcc-2.21.33363.0+82129205/MODULE_cae8a0ee9677f6f7b542+6170d8e1/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:248855ab5dc5241d90d7946bdcb39ee97ebd8761a30c53e4adc24d310451fcb8
3
  size 2049024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68343986474726278f99537638223997b40aff3ce0002aa57d6454b1692f960b
3
  size 2049024
neuronxcc-2.21.33363.0+82129205/MODULE_ce7e2a2399f408878a1f+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f1b1d60e24ca26b6d24cb49e566580a8186b53bd77a98f8846cfac45aba635a
3
  size 2612224
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e293b66e0df86f7fa9301d0cd2ed15c6f30e25a8d2bdd5193f1f62de244ca9
3
  size 2612224
neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/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/chunked_prefill/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:798527838569cf26e266fa715b5182d8ff48541532a3dbbf5e50c337b64a9b7e
3
+ size 528804
neuronxcc-2.21.33363.0+82129205/MODULE_d25f93bd990de6a53f0e+6170d8e1/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:290896a9e3b97a084af69caeef4b2aba62124e1381d4aec09c82e19b66760243
3
+ size 3994624
neuronxcc-2.21.33363.0+82129205/MODULE_f9b5b25ceb35d0bb7f65+a02c3a36/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b2412e661b900b3af3139b1d91bdb93c5ed605c4b1865838d1e1547d8bddb2d
3
  size 2366464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c739038d7d0c4558a9741ce55370950d838523f79ebf89b548ac9703421bf7
3
  size 2366464
neuronxcc-2.21.33363.0+82129205/MODULE_f9b5b25ceb35d0bb7f65+a02c3a36/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f876bcfcef6adcc92879cc76bc6a8e37ca4579da8523aebda542c9a7fb43556
3
  size 2440436
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d3c500859dd6337c0bf4801346d00c542e7e2349e996c6f9616b5021b1c7c87
3
  size 2440436