Commit
9590944
·
verified ·
1 Parent(s): 7a4a969

Synchronizing local compiler cache.

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/b851469c36fca337cb63.json +77 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/b451984f224fe0f3ba20.json +71 -0
  4. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/cc411d7a2728d29949b1.json +71 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.hlo_module.pb +1 -1
  6. neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.neff +1 -1
  7. neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/wrapped_neff.hlo +1 -1
  8. neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.hlo_module.pb +1 -1
  9. neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.neff +1 -1
  10. neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/wrapped_neff.hlo +1 -1
  11. neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff +0 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff +0 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff +0 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.hlo_module.pb +1 -1
  15. neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.neff +1 -1
  16. neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/wrapped_neff.hlo +1 -1
  17. neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/compile_flags.json +1 -0
  18. neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.done +0 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.hlo_module.pb +3 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.neff +3 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/wrapped_neff.hlo +3 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.hlo_module.pb +1 -1
  23. neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.neff +1 -1
  24. neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/wrapped_neff.hlo +1 -1
  25. neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.hlo_module.pb +1 -1
  26. neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.neff +1 -1
  27. neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/wrapped_neff.hlo +1 -1
  28. neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff +0 -0
  29. neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.hlo_module.pb +1 -1
  30. neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.neff +1 -1
  31. neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/wrapped_neff.hlo +1 -1
  32. neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.hlo_module.pb +1 -1
  33. neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.neff +1 -1
  34. neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/wrapped_neff.hlo +1 -1
  35. neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/compile_flags.json +1 -0
  36. neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.done +0 -0
  37. neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.hlo_module.pb +3 -0
  38. neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.neff +3 -0
  39. neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/compile_flags.json +1 -0
  40. neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.done +0 -0
  41. neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.hlo_module.pb +3 -0
  42. neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.neff +3 -0
  43. neuronxcc-2.17.194.0+d312836f/MODULE_5c7cdf7c9d803720623f+431f5505/model.neff +1 -1
  44. neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.hlo_module.pb +1 -1
  45. neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.neff +1 -1
  46. neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/wrapped_neff.hlo +1 -1
  47. neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/compile_flags.json +1 -0
  48. neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.done +0 -0
  49. neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.hlo_module.pb +3 -0
  50. neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.neff +3 -0
.gitattributes CHANGED
@@ -3571,3 +3571,12 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.neff f
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
 
 
 
 
 
 
 
 
 
 
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
3574
+ neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3575
+ neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3576
+ neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3577
+ neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
3578
+ neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3579
+ neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3580
+ neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3581
+ neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
3582
+ neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/b851469c36fca337cb63.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": "2.17.194.0+d312836f",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.3.0.dev4",
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-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/b451984f224fe0f3ba20.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": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev4",
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-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/cc411d7a2728d29949b1.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": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev4",
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-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc7e7185210f12f6a2eb02ea192cca41c851d62bef86ae4edd72fa5c1658a398
3
  size 52490
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ded2249dce62acb4342c71d4845a9b35d614bc879f96bb51b59ac7ef116de083
3
  size 52490
neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3df70213923e9aad11f04521bcb75900cf7041d3fbab614a66a11045c652707d
3
  size 185344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fcc7e4611905ceb085a5044d5d67da7672e63f17b106d1449d74faa15833ff0
3
  size 185344
neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83da799e58f62ac78702dcb279044d009f4bfea7bbab3d13204d8f89027ca834
3
  size 195507
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1bdfa94a6edc83f03954bec307333ccae2afbd91e744fdd799dd7dbcf8d3bdf8
3
  size 195507
neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7247332e2a30e23667bcf96312db2825f0dff9a5edd81bea17bcf5e84a200a4
3
  size 81342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56f78b3c986abcbbb3ae075a5f2302e28dba79156f23719feceafc0419b3986
3
  size 81342
neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e9a55404a52572809ba5ea4756e4e9e2b648d9f971e6c366defad000bfe8511
3
  size 236544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02f47938ce74cafed0379c011af8988bac4c7900709b2e317e41ca27ebae42da
3
  size 236544
neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5f68c9acb488bf85677917464c641c5623dca68d9f1c798dc5537ac2e951540
3
  size 244319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46924898a1be77320b737213fac787a3e8fbfb09a18da68ee658c15a2fb8a075
3
  size 244319
neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff CHANGED
Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff differ
 
neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff CHANGED
Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff differ
 
neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff CHANGED
Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff differ
 
neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18326d5fb6180fc809a5dfa2ec9bbde3caacf1caa0263ecdcb34b77e5b13e7c7
3
  size 79534
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ac6cdda1eadecd195ecca6c4d9af6883e0ae0c8f779dedf4ea860d7646359a1
3
  size 79534
neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c00586c7331ea06da3376b2c5b88c9ba30533b6fb8731955c589b37a9164758
3
  size 216064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd31746ed43c76de3a02592868cc53552bec3006fbabac36eb6f3d6f6504c3c4
3
  size 216064
neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c85fb0e6853d63b01037a7f56e7693f357d47b0b61cfea76bae11557e43d3f54
3
  size 223770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddb7a3c2b19ce82ac135f580e31b96d1925da1777cacb610b176583f3e9aa607
3
  size 223770
neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e2d997c17bac2017d5043a78f8d08c9b2ba3ccdafd20280ea49c9f33d694cd5
3
+ size 81540
neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92331e32d419d418e6eef5ad59dafbf2ce56f01b5cf1e29ef4def72f5e3db37e
3
+ size 461824
neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22e24a6e3362ae8db167e74e247bcd7c095785d8b5f998279da74a7b84500e6d
3
+ size 469663
neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4190870df7e587c49fbeb3aa4eb5996292c91ca7cb812297c3d52df0f9e3675
3
  size 89230
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48d570de437bee27addca79567e3f95bc342a186a40d0bc067cfb000ed5f0ea4
3
  size 89230
neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3be6ef9cb6d9f18cf8d09ef9306aef0bd1977685275d5a18dc823411b74bae2a
3
  size 236544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f74a711966837a1e383e92cdb3866925a8233dabd2e0168536fe14215d92fb0
3
  size 236544
neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:44ee4ed8736267c9d576c3570ae301231b4b4d78b17d5f2ed88b40fa9300764d
3
  size 247153
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64fc0daf96791c594fb34f68afeaeda8a25af72e3f49586c18c823506102faad
3
  size 247153
neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a246bea7a7b699f74516fd8df7a3ef93b9cb13b04c33860e496161f4ff8e53d
3
  size 47085
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cf231e78d797aeaaa85a9adcd3061fe1a5c80d41e33827406344b7d993a3423
3
  size 47085
neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:740142233ab5e4d2667725beb273f35c21a2b90efec957b376cc07650312a00d
3
  size 144384
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2c98b55b32183253a40dd36f7a1ffbdee46446ffe5e34d0fad688a46bb33d1
3
  size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:883956d16990891b8849db61efef36bde4b7c82ef4611e406fd685f61d2f9592
3
  size 152045
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83b68ec6506252488f8e7b695eddb67f0be404486a69e47f27f192ec08eb29ff
3
  size 152045
neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff CHANGED
Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff differ
 
neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f90785b02824797ea0ae29760d7ce36695ac71f4da76c7cb6589fb60a90c57b6
3
  size 79534
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5d17778bee19e679b21f8df23dcf0f686f5f5fde465ee27c15a4af3ae283700
3
  size 79534
neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:129e28e61e50f1c96f703481094ba4129093724f04ee4941f0acabab64ebc643
3
  size 216064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d052436ad985e98350d77b633476e9d31be12c8b67be9ac9c3d7bd8279109d9e
3
  size 216064
neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4946e6a857af4ea5708290e96abd80ace538f381924d26a04c26b766de975387
3
  size 223770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e52ed63dab973aaf0e89d040d580c2affaf2aadd73626a6a261271c450451ca
3
  size 223770
neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34b8863e5e31ca539aec62a5330c04e1f4f7761bf994412bd4f1825d4773e28d
3
  size 68831
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:146feab8982c942ad32a864ef4d88695887e1681a5d618f18a99a0a1708d4fd3
3
  size 68831
neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c15c052e9c900cb4d557acfd90d1cbccabcb7d72d3a5269f3ca131f475a08b5d
3
  size 257024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e076bef02ff9d09365b69af770dd7dc5f58043842933e2e976950adb9e10520
3
  size 257024
neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76d1eb8404998b4bbd242185690a39d1eb086638690e04b96366db5e7b41bdc8
3
  size 268322
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fb4a3079307d33ea3f574db4d2d33a5f09bc40f08f5434fdbe857a0ddddfc6a
3
  size 268322
neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f62885052a881aa88a96bfb03f808af3c2e6fb11ff20b71411aad180cd5c7f
3
+ size 687486
neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:094a9e95b4e8218f9ac4e12b3176aa08ee8b9d6a01f7498db8b26175d28c7797
3
+ size 19487744
neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eba0f369eb0bcb64aa67cb117612f2281e3dcde73bcde7d96fb7dc52b7982ec0
3
+ size 91298
neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a2f3511db4181fcaeb3a69b114dd657c77c3f65393ac50196ed77dc45937d94
3
+ size 213842944
neuronxcc-2.17.194.0+d312836f/MODULE_5c7cdf7c9d803720623f+431f5505/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce0e919044931f1c6ce8f82aaafc8ac84d23f1351c2ccc221f929723cbb04437
3
  size 103424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:999f5c5e325eb369b07ce8abcbad1703a953548b28c30e15fbf47b4a6bd9478b
3
  size 103424
neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32329dbcfe40d77d5b7fab482041cbbc6d84800ceed3a20a19261f5e3ddd36a7
3
  size 81342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bdfeeb5401951679a6e81aab655275f13a93cdc7c81b78b897b3f032529f7dce
3
  size 81342
neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88a629f47632431528581d85facd7912458f11cf897aa8be6a0fa8d39a1f0076
3
  size 236544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:211509fb27b7dc5340ecebb4dbc9c8dd8f3b4065fd89d120fbd1f878a12f7169
3
  size 236544
neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72a94cf38fd5003389afb8aecd8f850f855043d511e4f2e4e637f9831094622e
3
  size 244319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6da46b789ea4310b288c33f09c460aea9391e30a3c84ebd08483b4f7aaa1ce0e
3
  size 244319
neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8accf4a8e05ca6c46132e9f38bea7e7a3c419937a39ac087f4c2cc195bddbb1b
3
+ size 619941
neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c137346df7c096cc2a1e11ae5134c442c3a274865ffce05b77dd8efd11f7245c
3
+ size 1117184