Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
dacorvo HF Staff commited on
Commit
d10e9c2
·
verified ·
1 Parent(s): 8ec5ee1

Synchronizing local compiler cache.

Browse files
Files changed (31) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/170003f56784bc220718.json +82 -0
  3. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/69e6364014342d864b02.json +82 -0
  4. neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/852bbe8390fac2afac2d.json +82 -0
  5. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/compile_flags.json +1 -0
  6. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.done +0 -0
  7. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.hlo_module.pb +3 -0
  8. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.neff +3 -0
  9. neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/wrapped_neff.hlo +3 -0
  10. neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/compile_flags.json +1 -0
  11. neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.done +0 -0
  12. neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.hlo_module.pb +3 -0
  13. neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.neff +3 -0
  14. neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/compile_flags.json +1 -0
  15. neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.done +0 -0
  16. neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.hlo_module.pb +3 -0
  17. neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.neff +3 -0
  18. neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/compile_flags.json +1 -0
  19. neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.done +0 -0
  20. neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.hlo_module.pb +3 -0
  21. neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.neff +3 -0
  22. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/compile_flags.json +1 -0
  23. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.done +0 -0
  24. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.hlo_module.pb +3 -0
  25. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff +3 -0
  26. neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo +3 -0
  27. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/compile_flags.json +1 -0
  28. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.done +0 -0
  29. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.hlo_module.pb +3 -0
  30. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff +3 -0
  31. neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -5245,3 +5245,12 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/model.neff
5245
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5246
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5247
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
5245
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_95f9c1fd8552c597729b+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5246
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_cddd1fe7affe9c43a1cb+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5247
  neuronxcc-2.21.18209.0+043b1bf7/MODULE_724c5275183284d9e287+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5248
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5249
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5250
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5251
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5252
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.neff filter=lfs diff=lfs merge=lfs -text
5253
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5254
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
5255
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff filter=lfs diff=lfs merge=lfs -text
5256
+ neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/170003f56784bc220718.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "layer_types": [
14
+ "full_attention",
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "neuron": {
43
+ "_serialized_key": "NxDNeuronConfig",
44
+ "batch_size": 1,
45
+ "capacity_factor": null,
46
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
47
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
48
+ "continuous_batching": false,
49
+ "enable_bucketing": false,
50
+ "ep_degree": 1,
51
+ "fused_qkv": false,
52
+ "glu_mlp": true,
53
+ "local_ranks_size": 2,
54
+ "max_batch_size": 1,
55
+ "max_context_length": 4096,
56
+ "max_topk": 256,
57
+ "n_active_tokens": 4096,
58
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
59
+ "on_device_sampling": true,
60
+ "optimum_neuron_version": "0.4.1.dev0",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "sequence_length": 4096,
64
+ "speculation_length": 0,
65
+ "start_rank_id": 0,
66
+ "target": "trn2",
67
+ "torch_dtype": "bfloat16",
68
+ "tp_degree": 2
69
+ },
70
+ "num_attention_heads": 14,
71
+ "num_hidden_layers": 24,
72
+ "num_key_value_heads": 2,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "use_cache": true,
79
+ "use_mrope": false,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 151936
82
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/69e6364014342d864b02.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "layer_types": [
14
+ "full_attention",
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "neuron": {
43
+ "_serialized_key": "NxDNeuronConfig",
44
+ "batch_size": 2,
45
+ "capacity_factor": null,
46
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
47
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
48
+ "continuous_batching": true,
49
+ "enable_bucketing": false,
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": "2.21.18209.0+043b1bf7",
59
+ "on_device_sampling": false,
60
+ "optimum_neuron_version": "0.4.1.dev0",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "sequence_length": 1024,
64
+ "speculation_length": 0,
65
+ "start_rank_id": 0,
66
+ "target": "trn2",
67
+ "torch_dtype": "float16",
68
+ "tp_degree": 2
69
+ },
70
+ "num_attention_heads": 14,
71
+ "num_hidden_layers": 24,
72
+ "num_key_value_heads": 2,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "use_cache": true,
79
+ "use_mrope": false,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 151936
82
+ }
neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/qwen2/Qwen/Qwen2.5-0.5B/852bbe8390fac2afac2d.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "layer_types": [
14
+ "full_attention",
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
+ ],
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 24,
41
+ "model_type": "qwen2",
42
+ "neuron": {
43
+ "_serialized_key": "NxDNeuronConfig",
44
+ "batch_size": 1,
45
+ "capacity_factor": null,
46
+ "checkpoint_id": "Qwen/Qwen2.5-0.5B",
47
+ "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
48
+ "continuous_batching": false,
49
+ "enable_bucketing": false,
50
+ "ep_degree": 1,
51
+ "fused_qkv": false,
52
+ "glu_mlp": true,
53
+ "local_ranks_size": 2,
54
+ "max_batch_size": 1,
55
+ "max_context_length": 4096,
56
+ "max_topk": 256,
57
+ "n_active_tokens": 4096,
58
+ "neuronxcc_version": "2.21.18209.0+043b1bf7",
59
+ "on_device_sampling": true,
60
+ "optimum_neuron_version": "0.4.1.dev0",
61
+ "output_logits": false,
62
+ "pp_degree": 1,
63
+ "sequence_length": 4096,
64
+ "speculation_length": 0,
65
+ "start_rank_id": 0,
66
+ "target": "trn2",
67
+ "torch_dtype": "float32",
68
+ "tp_degree": 2
69
+ },
70
+ "num_attention_heads": 14,
71
+ "num_hidden_layers": 24,
72
+ "num_key_value_heads": 2,
73
+ "rms_norm_eps": 1e-06,
74
+ "rope_scaling": null,
75
+ "rope_theta": 1000000.0,
76
+ "sliding_window": null,
77
+ "tie_word_embeddings": true,
78
+ "use_cache": true,
79
+ "use_mrope": false,
80
+ "use_sliding_window": false,
81
+ "vocab_size": 151936
82
+ }
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51f9d21d7a03b72e80759a6fa19a09c7e71d8a2e874388f760eb03e4e4c92766
3
+ size 1828641
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:433aa40bc35fc194582a36bab350f5179d942bbdcd577e9ee1a0a5e4265393ab
3
+ size 2448384
neuronxcc-2.21.18209.0+043b1bf7/MODULE_1f2b543ce9d16a1e5c9d+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac1d73380b8f8ff586ab85f97f5bbbdcda51c7bc6415c4a892896b2a384410e7
3
+ size 2604836
neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab3f5c5b7f60b8bf1f3a23967f03bbe347a788088d7764f634b462ff7ab04d2
3
+ size 985198
neuronxcc-2.21.18209.0+043b1bf7/MODULE_340dc8482780758de90a+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d363135efcf905916ec3d7963c3729b2dbcfba86ea92e5196eba15b38d0e41d
3
+ size 5397504
neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a42447f12f8604b34318539a5637fb83bd81f35748cc41ec8788c063b2c5b7
3
+ size 2187414
neuronxcc-2.21.18209.0+043b1bf7/MODULE_539368c5d1779b85187d+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31dcbda78281314eadd5e7936d6011f89210c120f30e348211c1c2b614108b9a
3
+ size 23716864
neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e1f8ab9178c91201dfce6b4ff42207669032c0d34dac775fb25114204b1253e
3
+ size 2227261
neuronxcc-2.21.18209.0+043b1bf7/MODULE_59c347070845afc4c9a8+877608f3/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5507bfbebf110c0c3bffaea3d42344ee8a7427ef33be6d08f241b494d2594fa6
3
+ size 21586944
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a05d55a3ba9ed1af510844c9797965d4cf4c24eb231b3e0e25021c14e5d55ed
3
+ size 588406
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5b0f264fb42d12b5916bcbf73cd0e6b0189dad48d343359923f289414870bdf
3
+ size 2305024
neuronxcc-2.21.18209.0+043b1bf7/MODULE_8ac694dbef724ba479f1+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b813129942113c15e66cf44ac3729e7efa743c3b5fb837929016cf014a5f7a7
3
+ size 2461361
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.done ADDED
File without changes
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:221d9900764dc5760a3d695ae2053b499329036623d488849574309e9e92bbc9
3
+ size 1875753
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc6f75477819607337d0653d6d131f3dd4722cfdc986bdf65b7adeb56fc6b9a7
3
+ size 2294784
neuronxcc-2.21.18209.0+043b1bf7/MODULE_9cd66e993df1b139ff6c+747527b0/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e80bfad5095c3f6a5ac472d4d43b2bc2a685e8502357bead47768e21139ff49a
3
+ size 2451236