Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files
xet
Community
optimum-internal-testing-user commited on
Commit
36445d8
·
verified ·
1 Parent(s): 4bb52f7

Synchronizing local compiler cache.

Browse files
Files changed (43) hide show
  1. .gitattributes +9 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/07e1bb9368491ee6034e.json +75 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/28579f53b8227aa63fa0.json +75 -0
  4. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/f40a235c0ab56d3c6516.json +75 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+431f5505/compile_flags.json +1 -0
  6. neuronxcc-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+431f5505/model.done +0 -0
  7. neuronxcc-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+431f5505/model.hlo_module.pb +3 -0
  8. neuronxcc-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+431f5505/model.neff +0 -0
  9. neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+bfe5714b/compile_flags.json +1 -0
  10. neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+bfe5714b/model.done +0 -0
  11. neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+bfe5714b/model.hlo_module.pb +3 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+bfe5714b/model.neff +3 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_15b1720610325f710435+431f5505/compile_flags.json +1 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_15b1720610325f710435+431f5505/model.done +0 -0
  15. neuronxcc-2.17.194.0+d312836f/MODULE_15b1720610325f710435+431f5505/model.hlo_module.pb +3 -0
  16. neuronxcc-2.17.194.0+d312836f/MODULE_15b1720610325f710435+431f5505/model.neff +0 -0
  17. neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/compile_flags.json +1 -0
  18. neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/model.done +0 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/model.hlo_module.pb +3 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/model.neff +3 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/wrapped_neff.hlo +3 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+bfe5714b/compile_flags.json +1 -0
  23. neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+bfe5714b/model.done +0 -0
  24. neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+bfe5714b/model.hlo_module.pb +3 -0
  25. neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+bfe5714b/model.neff +3 -0
  26. neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/compile_flags.json +1 -0
  27. neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/model.done +0 -0
  28. neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/model.hlo_module.pb +3 -0
  29. neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/model.neff +3 -0
  30. neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/wrapped_neff.hlo +3 -0
  31. neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+bfe5714b/compile_flags.json +1 -0
  32. neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+bfe5714b/model.done +0 -0
  33. neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+bfe5714b/model.hlo_module.pb +3 -0
  34. neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+bfe5714b/model.neff +3 -0
  35. neuronxcc-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+431f5505/compile_flags.json +1 -0
  36. neuronxcc-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+431f5505/model.done +0 -0
  37. neuronxcc-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+431f5505/model.hlo_module.pb +3 -0
  38. neuronxcc-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+431f5505/model.neff +0 -0
  39. neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/compile_flags.json +1 -0
  40. neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/model.done +0 -0
  41. neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/model.hlo_module.pb +3 -0
  42. neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/model.neff +3 -0
  43. neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/wrapped_neff.hlo +3 -0
.gitattributes CHANGED
@@ -2900,3 +2900,12 @@ neuronxcc-2.17.194.0+d312836f/MODULE_11e381f25d31953ed15d+431f5505/model.neff fi
2900
  neuronxcc-2.17.194.0+d312836f/MODULE_716aad5e7da409a95352+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2901
  neuronxcc-2.17.194.0+d312836f/MODULE_d9e30f7fe75dbb843a13+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2902
  neuronxcc-2.17.194.0+d312836f/MODULE_d9e30f7fe75dbb843a13+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
2900
  neuronxcc-2.17.194.0+d312836f/MODULE_716aad5e7da409a95352+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2901
  neuronxcc-2.17.194.0+d312836f/MODULE_d9e30f7fe75dbb843a13+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2902
  neuronxcc-2.17.194.0+d312836f/MODULE_d9e30f7fe75dbb843a13+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2903
+ neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2904
+ neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2905
+ neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2906
+ neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2907
+ neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2908
+ neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
2909
+ neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
2910
+ neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
2911
+ neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/07e1bb9368491ee6034e.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 1,
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": "yujiepan/qwen2.5-128k-tiny-random",
24
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
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": 100,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 100,
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.dev0",
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": "float16",
50
+ "sequence_length": 100,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "float16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 4,
60
+ "num_hidden_layers": 2,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": {
64
+ "factor": 4.0,
65
+ "original_max_position_embeddings": 32768,
66
+ "rope_type": "yarn",
67
+ "type": "yarn"
68
+ },
69
+ "rope_theta": 1000000.0,
70
+ "sliding_window": 131072,
71
+ "tie_word_embeddings": false,
72
+ "use_cache": true,
73
+ "use_sliding_window": false,
74
+ "vocab_size": 152064
75
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/28579f53b8227aa63fa0.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 1,
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": "yujiepan/qwen2.5-128k-tiny-random",
24
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
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": 100,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 100,
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.dev0",
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": 100,
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": 4,
60
+ "num_hidden_layers": 2,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": {
64
+ "factor": 4.0,
65
+ "original_max_position_embeddings": 32768,
66
+ "rope_type": "yarn",
67
+ "type": "yarn"
68
+ },
69
+ "rope_theta": 1000000.0,
70
+ "sliding_window": 131072,
71
+ "tie_word_embeddings": false,
72
+ "use_cache": true,
73
+ "use_sliding_window": false,
74
+ "vocab_size": 152064
75
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/yujiepan/qwen2.5-128k-tiny-random/f40a235c0ab56d3c6516.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 1,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 2,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
24
+ "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
25
+ "continuous_batching": true,
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": 2,
35
+ "max_context_length": 100,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 100,
40
+ "neuronxcc_version": "2.17.194.0+d312836f",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": false,
43
+ "optimum_neuron_version": "0.3.0.dev0",
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": "float16",
50
+ "sequence_length": 100,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "float16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 4,
60
+ "num_hidden_layers": 2,
61
+ "num_key_value_heads": 2,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": {
64
+ "factor": 4.0,
65
+ "original_max_position_embeddings": 32768,
66
+ "rope_type": "yarn",
67
+ "type": "yarn"
68
+ },
69
+ "rope_theta": 1000000.0,
70
+ "sliding_window": 131072,
71
+ "tie_word_embeddings": false,
72
+ "use_cache": true,
73
+ "use_sliding_window": false,
74
+ "vocab_size": 152064
75
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+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-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1b1213e5cb958c24a3c0e6b756eecb2212ee22b9ada51d486ccee91308b7d59
3
+ size 10365
neuronxcc-2.17.194.0+d312836f/MODULE_0126b6d6206c1b88e8d7+431f5505/model.neff ADDED
Binary file (42 kB). View file
 
neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+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_05a9fb04061401c43721+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58dc4360bd140cb72dd8c3d5cb30f19cc41407c87a7fc472289c81d2d3d281d0
3
+ size 60490
neuronxcc-2.17.194.0+d312836f/MODULE_05a9fb04061401c43721+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:339febe661cddc6f7ae64bcb10f7b31fcfae187a2ae5e8f7be746e3380d349ae
3
+ size 144384
neuronxcc-2.17.194.0+d312836f/MODULE_15b1720610325f710435+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-2.17.194.0+d312836f/MODULE_15b1720610325f710435+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_15b1720610325f710435+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47099763ee1c72b3faf939148d519a43c8f4be88b57401f435bc419a4c0b7db3
3
+ size 10365
neuronxcc-2.17.194.0+d312836f/MODULE_15b1720610325f710435+431f5505/model.neff ADDED
Binary file (42 kB). View file
 
neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+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_2b3977221dd3c1ec9b59+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d382c3469203b8c45966cc5b3787b6efb84b52f1e9ecfab69a401fab5ba674a4
3
+ size 95677
neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9666c41d440dcba3b0edcf500708e4c1b1a2f5543cecdb6c897c4f4274b89e
3
+ size 216064
neuronxcc-2.17.194.0+d312836f/MODULE_2b3977221dd3c1ec9b59+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4d83b390f16aa36410d978375100dabfa09da294acc4292b6a6a57fa8b14953
3
+ size 226676
neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+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_3de765452a0b4c3d7fc6+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e9dad030b87d8e796347b1116457ebcbb521c474488ce33993be570bfa3178b
3
+ size 94265
neuronxcc-2.17.194.0+d312836f/MODULE_3de765452a0b4c3d7fc6+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b9b07098d95a31e6934c5ebf0475f796004f0bcee37b234ecdfbb21347412ef
3
+ size 226304
neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+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_5dce8475ab0c418ab82d+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f429c9857ba5c9d440ba183cec50a69a310569571965e5ffdb2d97b441a24d0
3
+ size 62840
neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b7686326eb8276e5ca8532992e8af0fe1953c81a995dd2865fbe98c7a598435
3
+ size 2356224
neuronxcc-2.17.194.0+d312836f/MODULE_5dce8475ab0c418ab82d+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a11efec7d3cf113bbd21aa01943adb729e97e822d65a396745ba7166690c6c
3
+ size 2366507
neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+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_b946a9867e7e82def54d+bfe5714b/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+bfe5714b/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4538811676283b1a915d51956cf9c1362046e62414c846c6474c725069edf883
3
+ size 94265
neuronxcc-2.17.194.0+d312836f/MODULE_b946a9867e7e82def54d+bfe5714b/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d8dc9cc84e7cc6cc99bbc7ca4eb85152266d82d9813c73886493cf0e676ca1a
3
+ size 226304
neuronxcc-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+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-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08538c1bac16866f3802d154c22153797061f69b127756adaaebb6e1ea146adc
3
+ size 10013
neuronxcc-2.17.194.0+d312836f/MODULE_c9c2881bb5bc3392d929+431f5505/model.neff ADDED
Binary file (42 kB). View file
 
neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+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_df74b6c7d98ed2e941de+165e9558/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60e33c8f3af92ecb9a57491bfd93c650af06c2cb705c852969a0bcac449d5b6f
3
+ size 95677
neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e0591f32bbd8305435794266dbf5e7f4d443906b8df16ff47414e786ebce2af
3
+ size 216064
neuronxcc-2.17.194.0+d312836f/MODULE_df74b6c7d98ed2e941de+165e9558/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a34dbd446e3190d59fbad6cf771005d5420e821579fd2dd1f7ee0248c2898d9
3
+ size 226676