Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
optimum-internal-testing-user commited on
Commit
9e80fe5
·
verified ·
1 Parent(s): adb41d8

Synchronizing local compiler cache.

Browse files
Files changed (31) hide show
  1. .gitattributes +7 -0
  2. neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/3fa0011c99feb6646d82.json +77 -0
  3. neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-0.5B/649c5e56a8df75276c09.json +71 -0
  4. neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-0.5B/fcef128946fbd2c051eb.json +71 -0
  5. neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/compile_flags.json +1 -0
  6. neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.done +0 -0
  7. neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.hlo_module.pb +3 -0
  8. neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.neff +3 -0
  9. neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff +0 -0
  10. neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/compile_flags.json +1 -0
  11. neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.done +0 -0
  12. neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.hlo_module.pb +3 -0
  13. neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.neff +3 -0
  14. neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/wrapped_neff.hlo +3 -0
  15. neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/model.neff +1 -1
  16. neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/wrapped_neff.hlo +1 -1
  17. neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.hlo_module.pb +1 -1
  18. neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.neff +1 -1
  19. neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/compile_flags.json +1 -0
  20. neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.done +0 -0
  21. neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.hlo_module.pb +3 -0
  22. neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.neff +3 -0
  23. neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/wrapped_neff.hlo +3 -0
  24. neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/compile_flags.json +1 -0
  25. neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/model.done +0 -0
  26. neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/model.hlo_module.pb +3 -0
  27. neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/model.neff +3 -0
  28. neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/compile_flags.json +1 -0
  29. neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.done +0 -0
  30. neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.hlo_module.pb +3 -0
  31. neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff +3 -0
.gitattributes CHANGED
@@ -3160,3 +3160,10 @@ neuronxcc-2.18.121.0+9e31e41a/MODULE_6eed81733d4e8aaab34a+84f3e719/model.neff fi
3160
  neuronxcc-2.18.121.0+9e31e41a/MODULE_a57600b672ea2ee05d8c+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
3161
  neuronxcc-2.18.121.0+9e31e41a/MODULE_a57600b672ea2ee05d8c+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3162
  neuronxcc-2.18.121.0+9e31e41a/MODULE_f55bef5a76fbf9bf2649+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
3160
  neuronxcc-2.18.121.0+9e31e41a/MODULE_a57600b672ea2ee05d8c+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
3161
  neuronxcc-2.18.121.0+9e31e41a/MODULE_a57600b672ea2ee05d8c+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3162
  neuronxcc-2.18.121.0+9e31e41a/MODULE_f55bef5a76fbf9bf2649+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
3163
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
3164
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
3165
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3166
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
3167
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
3168
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
3169
+ neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/llama/llamafactory/tiny-random-Llama-3/3fa0011c99feb6646d82.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": "2.18.121.0+9e31e41a",
43
+ "num_cores_per_group": 1,
44
+ "on_device_sampling": true,
45
+ "optimum_neuron_version": "0.3.0.dev1",
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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-0.5B/649c5e56a8df75276c09.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": "2.18.121.0+9e31e41a",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev1",
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-2.18.121.0+9e31e41a/0_REGISTRY/0.3.0.dev1/qwen2/Qwen/Qwen2.5-0.5B/fcef128946fbd2c051eb.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": "2.18.121.0+9e31e41a",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": true,
43
+ "optimum_neuron_version": "0.3.0.dev1",
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-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/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-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-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.done ADDED
File without changes
neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ad438ab09ba805e35aa5c056da9aaa135edda0fe87ed3d1597ef8922be31734
3
+ size 689263
neuronxcc-2.18.121.0+9e31e41a/MODULE_166aaa1015315277406d+84f3e719/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea93f6c8948d51a4155fd96d89cfa28f3c85f7c2d30f901e913a990cda64a69
3
+ size 19590144
neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff CHANGED
Binary files a/neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff and b/neuronxcc-2.18.121.0+9e31e41a/MODULE_228e41176dd02608ed1e+431f5505/model.neff differ
 
neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/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-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-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.done ADDED
File without changes
neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:727858703321272f7ef3ede84f7745d7c5e8d2ecc5e525f90d4dce09cfd58201
3
+ size 613415
neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45d5b9058e56432b0ecee8eec52dd0d28d5607a677ed2e91c3d0b801a56cded8
3
+ size 1086464
neuronxcc-2.18.121.0+9e31e41a/MODULE_269d46dfd0562d73b572+5be477de/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985424155329c6aa31e3db81b9725f036821c1c34e1da827a85fc5b3f7aaceaf
3
+ size 1231490
neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffe86137f31d2026aaad8659c47651b4d94c61f55e6c4ea514c6215f1a42ea9b
3
  size 461824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9acc3248dd65217ef8f99e699cf599f1042276f0242dc329c2415b0916484a7d
3
  size 461824
neuronxcc-2.18.121.0+9e31e41a/MODULE_6a4d8f5e434c05928a7a+5be477de/wrapped_neff.hlo CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28cf9d2998b40746684329776521a0fa1a0f8fa8065fba9c76b4e8ad4f84cdac
3
  size 469663
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c039410374dcf762bad0a8a1ca460bd7428a3a5d3e707f13467b2c2b5d270cbc
3
  size 469663
neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.hlo_module.pb CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e5c59e89c64fa3053e94edb34c12cf7cefe1ddb6a8463cee55fcf718c04748c
3
  size 91602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:680e74012140d8f46546d07484b03b3922fe76d2140f36d71daa840ce664bea2
3
  size 91602
neuronxcc-2.18.121.0+9e31e41a/MODULE_6c15ea8227f10a4d650e+84f3e719/model.neff CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ae74e23bed43f8f95a7b5947ad255294517462a333fa9cccd4cb24a1429df355
3
  size 213474304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33950f21a662e3dfab5c3079eb6a0e14244c9dd6afcecb017e4d7ad66380222a
3
  size 213474304
neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/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-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-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.done ADDED
File without changes
neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6a8bd2239fbefe43eec18b6dc18a14c1b72e42b678a0076e78199863690d5f
3
+ size 613415
neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c289c15830e8e1e8436a7499be61ed9a4d85c0726134623054ca66a0673dcbd
3
+ size 1178624
neuronxcc-2.18.121.0+9e31e41a/MODULE_b6a9a38c21ff109170a7+5be477de/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ceaed7382d02fc957d2ea251ec2fc675cad0bc5bc722793ff63e131181cf8f0a
3
+ size 1323650
neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/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-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-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/model.done ADDED
File without changes
neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c955068953b3c1da99e4d7e159f6878b9aa1efc92f63a8b33ffd552f2bfb0dd1
3
+ size 563640
neuronxcc-2.18.121.0+9e31e41a/MODULE_d4144639fc6b91e228b8+84f3e719/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30570bccbd0f92e45d57748f508be7d74455fa5d9b0ff106ef36c2ab437df35c
3
+ size 1158144
neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"
neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.done ADDED
File without changes
neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24f6952bed3b510f10199c95e6a92ba54c483288f157c5f127a25187b9b1049
3
+ size 149919
neuronxcc-2.18.121.0+9e31e41a/MODULE_f86c96f7ee62c6431f74+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2267ef602a5b10390fc2b2eb6e20f49c9fa3557264c952b76280c844f1de23d7
3
+ size 594944