Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
dacorvo HF Staff commited on
Commit
1b99c98
·
verified ·
1 Parent(s): afba861

Synchronizing local compiler cache.

Browse files
Files changed (34) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/52a3b7d021f51c90337f.json +63 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/5fdba651620df09da93d.json +63 -0
  4. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/daa276345bb9b68e9be5.json +63 -0
  5. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/e4b573e1a33bbda76243.json +63 -0
  6. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/8b175859f95b9fa5a1db.json +63 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+24129607/compile_flags.json +1 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+24129607/model.done +0 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+24129607/model.hlo_module.pb +3 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+24129607/model.neff +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+24129607/compile_flags.json +1 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+24129607/model.done +0 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+24129607/model.hlo_module.pb +3 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+24129607/model.neff +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/compile_flags.json +1 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/model.done +0 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/model.hlo_module.pb +3 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/model.neff +3 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/wrapped_neff.hlo +3 -0
  20. neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+24129607/compile_flags.json +1 -0
  21. neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+24129607/model.done +0 -0
  22. neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+24129607/model.hlo_module.pb +3 -0
  23. neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+24129607/model.neff +3 -0
  24. neuronxcc-2.21.33363.0+82129205/MODULE_a6d912262b31e81edfe6+24129607/model.neff +1 -1
  25. neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/compile_flags.json +1 -0
  26. neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/model.done +0 -0
  27. neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/model.hlo_module.pb +3 -0
  28. neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/model.neff +3 -0
  29. neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/wrapped_neff.hlo +3 -0
  30. neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/compile_flags.json +1 -0
  31. neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/model.done +0 -0
  32. neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/model.hlo_module.pb +3 -0
  33. neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/model.neff +3 -0
  34. neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -6029,3 +6029,12 @@ neuronxcc-2.22.12471.0+b4a00d10/MODULE_f84b3d15315ce03d158d+84337dd9/wrapped_nef
6029
  neuronxcc-2.22.12471.0+b4a00d10/MODULE_3a2fc8ca7077639ece34+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
6030
  neuronxcc-2.22.12471.0+b4a00d10/MODULE_3a2fc8ca7077639ece34+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6031
  neuronxcc-2.22.12471.0+b4a00d10/MODULE_482523f5785e7f26485d+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
6029
  neuronxcc-2.22.12471.0+b4a00d10/MODULE_3a2fc8ca7077639ece34+84337dd9/model.neff filter=lfs diff=lfs merge=lfs -text
6030
  neuronxcc-2.22.12471.0+b4a00d10/MODULE_3a2fc8ca7077639ece34+84337dd9/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6031
  neuronxcc-2.22.12471.0+b4a00d10/MODULE_482523f5785e7f26485d+519f203d/model.neff filter=lfs diff=lfs merge=lfs -text
6032
+ neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6033
+ neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6034
+ neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6035
+ neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6036
+ neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
6037
+ neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6038
+ neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6039
+ neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
6040
+ neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/52a3b7d021f51c90337f.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "meta-llama/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": 32,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659",
25
+ "continuous_batching": true,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 32,
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": "0.4.4.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "sequence_parallel_enabled": false,
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": 32,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 8.0,
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": false,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/5fdba651620df09da93d.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "meta-llama/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": 32,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659",
25
+ "continuous_batching": true,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 8,
30
+ "max_batch_size": 32,
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": "0.4.4.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "sequence_parallel_enabled": false,
41
+ "speculation_length": 0,
42
+ "start_rank_id": 0,
43
+ "target": "trn1",
44
+ "torch_dtype": "bfloat16",
45
+ "tp_degree": 8
46
+ },
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 32,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 8.0,
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": false,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/daa276345bb9b68e9be5.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "meta-llama/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": 32,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659",
25
+ "continuous_batching": true,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 8,
30
+ "max_batch_size": 32,
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": "0.4.4.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "sequence_parallel_enabled": false,
41
+ "speculation_length": 0,
42
+ "start_rank_id": 0,
43
+ "target": "trn1",
44
+ "torch_dtype": "bfloat16",
45
+ "tp_degree": 8
46
+ },
47
+ "num_attention_heads": 32,
48
+ "num_hidden_layers": 32,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 8.0,
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": false,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/meta-llama/Llama-3.1-8B-Instruct/e4b573e1a33bbda76243.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "meta-llama/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": 32,
22
+ "capacity_factor": null,
23
+ "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct",
24
+ "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659",
25
+ "continuous_batching": true,
26
+ "ep_degree": 1,
27
+ "fused_qkv": true,
28
+ "glu_mlp": true,
29
+ "local_ranks_size": 2,
30
+ "max_batch_size": 32,
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": "0.4.4.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "sequence_parallel_enabled": false,
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": 32,
49
+ "num_key_value_heads": 8,
50
+ "pretraining_tp": 1,
51
+ "rms_norm_eps": 1e-05,
52
+ "rope_scaling": {
53
+ "factor": 8.0,
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": false,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/8b175859f95b9fa5a1db.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
25
+ "continuous_batching": true,
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": 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": "0.4.4.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn1",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 2
45
+ },
46
+ "num_attention_heads": 32,
47
+ "num_hidden_layers": 16,
48
+ "num_key_value_heads": 8,
49
+ "pretraining_tp": 1,
50
+ "rms_norm_eps": 1e-05,
51
+ "rope_scaling": {
52
+ "factor": 32.0,
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": true,
60
+ "unsloth_fixed": true,
61
+ "use_cache": true,
62
+ "vocab_size": 128256
63
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+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_110fc80e89006393f738+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60325dbe4e341d0836f3b68cedc6beaa300459af2c947445da4a545a3f703c10
3
+ size 939272
neuronxcc-2.21.33363.0+82129205/MODULE_110fc80e89006393f738+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e189bba6f572c67c0bd6e9bba05b58d4283f34c50588dd6aa97a34007311ba28
3
+ size 6667264
neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+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_196d1b2148ed8629b154+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d18c81c6ab7ffca4593ffd12280271d86ca9a2700a2770da93fb314a9109ff67
3
+ size 509380
neuronxcc-2.21.33363.0+82129205/MODULE_196d1b2148ed8629b154+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d13b5a6f47ee0e1c7c9b783470687dfcad53929b4035be0b071bbacd718948
3
+ size 41585664
neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+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_5cfe268b844f7d2286a5+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92413edeab8bdd1ff79c68aeeb0633faf78e28df1df24ce6e6685975d7156ff1
3
+ size 426769
neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c238600da6a768547204d176f9f7adf55db06bcaf6e1cc9a978896b92c42e21
3
+ size 3073024
neuronxcc-2.21.33363.0+82129205/MODULE_5cfe268b844f7d2286a5+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54e033c437c96db2869f8b8620b5b2eb24b6fad3e04fd4f0b417f6df1c3558ef
3
+ size 3147125
neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+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_7c1ab0225123c184780f+24129607/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+24129607/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afbf1c2497a38503bf2c1c9685d3d551b5461b11c9eedd45100bee098d75959d
3
+ size 978844
neuronxcc-2.21.33363.0+82129205/MODULE_7c1ab0225123c184780f+24129607/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8741039102da2965de796bf40e6538a49f53e0cebf245a4a5d30530136794056
3
+ size 6718464
neuronxcc-2.21.33363.0+82129205/MODULE_a6d912262b31e81edfe6+24129607/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6fcd0208f93d0034e8ba27de29cacfb822d98c06bc860349612fef53ad374a7
3
  size 114013184
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ebe7aa5e1ba33d7e2cb909b8df9ee8d25f1f1878a4dde47c74622a01bd3d37
3
  size 114013184
neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+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_cfd70138eb9722ac2255+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8406378e6e18cc6ac3eda37f281d580f7b4bbec015dc27ac8369fc44b705526f
3
+ size 809145
neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8a3a82e0d0626a80a2c5e6898d41e9ca22a72fea4b945f1555508c37787c263
3
+ size 21863424
neuronxcc-2.21.33363.0+82129205/MODULE_cfd70138eb9722ac2255+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec03e8b7d7deca9b162d16f1d57b4954f12796e59c0cd1e9bd7edbca49eff15
3
+ size 22011354
neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+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_dd366124647aeec64074+a02c3a36/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f057068b35f8aeb0d565f76649c32016184243a96809f860114d903a6770d7f
3
+ size 770051
neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695538f706036d1034f9ea8fb7269338dba1a78a37fc131646f03c7496f1239f
3
+ size 21801984
neuronxcc-2.21.33363.0+82129205/MODULE_dd366124647aeec64074+a02c3a36/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dca44e3cebd5178ce615300b84bd8ad2e980993e5fc672a7bb53b6576a4e981
3
+ size 21949799