Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
 Community
tengomucho HF Staff commited on
Commit
a4ede56
·
verified ·
1 Parent(s): fb16134

Synchronizing local compiler cache.

Browse files
Files changed (23) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/5b6c82d29f13b10e5052.json +87 -0
  3. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/b348680583357cdc479f.json +63 -0
  4. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/llama/unsloth/Llama-3.2-1B-Instruct/b348680583357cdc479f.json +63 -0
  5. neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/qwen3/Qwen/Qwen3-0.6B/5b6c82d29f13b10e5052.json +87 -0
  6. neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/compile_flags.json +1 -0
  7. neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/model.done +0 -0
  8. neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/model.hlo_module.pb +3 -0
  9. neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/model.neff +3 -0
  10. neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/wrapped_neff.hlo +3 -0
  11. neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/compile_flags.json +1 -0
  12. neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/model.done +0 -0
  13. neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/model.hlo_module.pb +3 -0
  14. neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/model.neff +3 -0
  15. neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/compile_flags.json +1 -0
  16. neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/model.done +0 -0
  17. neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/model.hlo_module.pb +3 -0
  18. neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/model.neff +3 -0
  19. neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/wrapped_neff.hlo +3 -0
  20. neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/compile_flags.json +1 -0
  21. neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.done +0 -0
  22. neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.hlo_module.pb +3 -0
  23. neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.neff +3 -0
.gitattributes CHANGED
@@ -6335,3 +6335,9 @@ neuronxcc-2.21.33363.0+82129205/MODULE_18ad931622c6ffd3a96c+ac10809c/wrapped_nef
6335
  neuronxcc-2.21.33363.0+82129205/MODULE_26a5b03803fa3c302f48+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
6336
  neuronxcc-2.21.33363.0+82129205/MODULE_26a5b03803fa3c302f48+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6337
  neuronxcc-2.21.33363.0+82129205/MODULE_bb55057d1263c7ecc9f1+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
6335
  neuronxcc-2.21.33363.0+82129205/MODULE_26a5b03803fa3c302f48+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
6336
  neuronxcc-2.21.33363.0+82129205/MODULE_26a5b03803fa3c302f48+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6337
  neuronxcc-2.21.33363.0+82129205/MODULE_bb55057d1263c7ecc9f1+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
6338
+ neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
6339
+ neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6340
+ neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
6341
+ neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
6342
+ neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
6343
+ neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/929b02754a13cbfdf657d863c3fc6f3bce672879bc6ae48ab45be21e881e9ec2/5b6c82d29f13b10e5052.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention"
45
+ ],
46
+ "max_position_embeddings": 40960,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 1,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
54
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 4,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 8192,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 8192,
64
+ "neuronxcc_version": "2.21.33363.0+82129205",
65
+ "on_device_sampling": true,
66
+ "optimum_neuron_version": "0.4.5.dev2",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 8192,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn2",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 4
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151936
87
+ }
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.5.dev2/cf6b9a360dcf294104671106bae2adbd9fd291823bb60a351883163684073231/b348680583357cdc479f.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": 4,
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": "0.4.5.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 4
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+82129205/0_REGISTRY/0.4.5.dev2/llama/unsloth/Llama-3.2-1B-Instruct/b348680583357cdc479f.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": 4,
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": "0.4.5.dev2",
37
+ "output_logits": false,
38
+ "pp_degree": 1,
39
+ "sequence_length": 4096,
40
+ "speculation_length": 0,
41
+ "start_rank_id": 0,
42
+ "target": "trn2",
43
+ "torch_dtype": "bfloat16",
44
+ "tp_degree": 4
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+82129205/0_REGISTRY/0.4.5.dev2/qwen3/Qwen/Qwen3-0.6B/5b6c82d29f13b10e5052.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen3-0.6B",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3ForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "dtype": "bfloat16",
11
+ "head_dim": 128,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1024,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 3072,
16
+ "layer_types": [
17
+ "full_attention",
18
+ "full_attention",
19
+ "full_attention",
20
+ "full_attention",
21
+ "full_attention",
22
+ "full_attention",
23
+ "full_attention",
24
+ "full_attention",
25
+ "full_attention",
26
+ "full_attention",
27
+ "full_attention",
28
+ "full_attention",
29
+ "full_attention",
30
+ "full_attention",
31
+ "full_attention",
32
+ "full_attention",
33
+ "full_attention",
34
+ "full_attention",
35
+ "full_attention",
36
+ "full_attention",
37
+ "full_attention",
38
+ "full_attention",
39
+ "full_attention",
40
+ "full_attention",
41
+ "full_attention",
42
+ "full_attention",
43
+ "full_attention",
44
+ "full_attention"
45
+ ],
46
+ "max_position_embeddings": 40960,
47
+ "max_window_layers": 28,
48
+ "model_type": "qwen3",
49
+ "neuron": {
50
+ "_serialized_key": "NxDNeuronConfig",
51
+ "batch_size": 1,
52
+ "capacity_factor": null,
53
+ "checkpoint_id": "Qwen/Qwen3-0.6B",
54
+ "checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
55
+ "continuous_batching": false,
56
+ "ep_degree": 1,
57
+ "fused_qkv": true,
58
+ "glu_mlp": true,
59
+ "local_ranks_size": 4,
60
+ "max_batch_size": 1,
61
+ "max_context_length": 8192,
62
+ "max_topk": 256,
63
+ "n_active_tokens": 8192,
64
+ "neuronxcc_version": "2.21.33363.0+82129205",
65
+ "on_device_sampling": true,
66
+ "optimum_neuron_version": "0.4.5.dev2",
67
+ "output_logits": false,
68
+ "pp_degree": 1,
69
+ "sequence_length": 8192,
70
+ "speculation_length": 0,
71
+ "start_rank_id": 0,
72
+ "target": "trn2",
73
+ "torch_dtype": "bfloat16",
74
+ "tp_degree": 4
75
+ },
76
+ "num_attention_heads": 16,
77
+ "num_hidden_layers": 28,
78
+ "num_key_value_heads": 8,
79
+ "rms_norm_eps": 1e-06,
80
+ "rope_scaling": null,
81
+ "rope_theta": 1000000,
82
+ "sliding_window": null,
83
+ "tie_word_embeddings": true,
84
+ "use_cache": true,
85
+ "use_sliding_window": false,
86
+ "vocab_size": 151936
87
+ }
neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ba098ae0e6d08336c9be8f2c36a2040c57bf742dac23919e9924876f3a9b8d2
3
+ size 2039561
neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:496b9843e391613fb587da84b12b1ada20791962e677a009fe8bd91185e2d0db
3
+ size 2601984
neuronxcc-2.21.33363.0+82129205/MODULE_b0b5c42826d33def683b+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17b51fda8fc0bf2dfb8f59119fb67724b0e1f847ce6bf30068751c6f8d8cf471
3
+ size 2677427
neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/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/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44496c8d54daef2f12dea482b0ba2483389a3a34970e64c9a705c1a0accd2673
3
+ size 1650539
neuronxcc-2.21.33363.0+82129205/MODULE_b61f26bf83def4e7a52c+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dafd314d1413d00ab29423d6159798b2e602b74cddf937f2704aa87a1b5f1ecb
3
+ size 18340864
neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d83b26422c55d914c1e05093c131d440e7c29bd979725446fa18acc06df74b9
3
+ size 1861448
neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ce57c1328015978a4d4af36aadd7b9a8c7f6b907bcee8f8c05e8e6b6841f8fd
3
+ size 2356224
neuronxcc-2.21.33363.0+82129205/MODULE_b95ab17ef3954bb04026+ac10809c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e85dd9315925b738f554f27889226341291e9b27c9af0bac757eb30fb4256ee2
3
+ size 2493000
neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/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/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.done ADDED
File without changes
neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1972b898fc2cf7d85cf15019e6c01bcb09f98a1ea3cce7aaa5b84f7bef8a40f0
3
+ size 2053375
neuronxcc-2.21.33363.0+82129205/MODULE_ed645ef81921b62e3ba7+a32116a7/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701cb845dd6f9c43beaad991db15f0de82f3f67b94d07243652aa34814205c8b
3
+ size 41411584