Hugging Face's logo

aws-neuron
/
optimum-neuron-cache

Model card Files Community
430
dacorvo HF Staff commited on
Commit
8f9dd02
·
verified ·
1 Parent(s): bbb001a

Synchronizing local compiler cache.

Browse files
Files changed (43) hide show
  1. .gitattributes +12 -0
  2. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev4/mixtral/dacorvo/Mixtral-tiny/3bd58a8f29b6ca08f6a0.json +75 -0
  3. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev4/mixtral/dacorvo/Mixtral-tiny/605773b6644d01e65e12.json +75 -0
  4. neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev4/mixtral/dacorvo/Mixtral-tiny/78dc7e071d7a0e3aef78.json +75 -0
  5. neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/compile_flags.json +1 -0
  6. neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/model.done +0 -0
  7. neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/model.hlo_module.pb +3 -0
  8. neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/model.neff +3 -0
  9. neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/wrapped_neff.hlo +3 -0
  10. neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/compile_flags.json +1 -0
  11. neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/model.done +0 -0
  12. neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/model.hlo_module.pb +3 -0
  13. neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/model.neff +3 -0
  14. neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/compile_flags.json +1 -0
  15. neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/model.done +0 -0
  16. neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/model.hlo_module.pb +3 -0
  17. neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/model.neff +3 -0
  18. neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/compile_flags.json +1 -0
  19. neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.done +0 -0
  20. neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.hlo_module.pb +3 -0
  21. neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.neff +3 -0
  22. neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/wrapped_neff.hlo +3 -0
  23. neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/compile_flags.json +1 -0
  24. neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.done +0 -0
  25. neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.hlo_module.pb +3 -0
  26. neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.neff +3 -0
  27. neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/compile_flags.json +1 -0
  28. neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/model.done +0 -0
  29. neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/model.hlo_module.pb +3 -0
  30. neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/model.neff +3 -0
  31. neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/wrapped_neff.hlo +3 -0
  32. neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+431f5505/compile_flags.json +1 -0
  33. neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+431f5505/model.done +0 -0
  34. neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+431f5505/model.hlo_module.pb +3 -0
  35. neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+431f5505/model.neff +3 -0
  36. neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+431f5505/compile_flags.json +1 -0
  37. neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+431f5505/model.done +0 -0
  38. neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+431f5505/model.hlo_module.pb +3 -0
  39. neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+431f5505/model.neff +3 -0
  40. neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/compile_flags.json +1 -0
  41. neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.done +0 -0
  42. neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.hlo_module.pb +3 -0
  43. neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.neff +3 -0
.gitattributes CHANGED
@@ -7902,3 +7902,15 @@ neuronxcc-2.17.194.0+d312836f/MODULE_052ac89b53a3ef1c39e5+613edded/model.neff fi
7902
  neuronxcc-2.17.194.0+d312836f/MODULE_d1a07b3f87341b20d662+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7903
  neuronxcc-2.17.194.0+d312836f/MODULE_7d5018ab15d06798796c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7904
  neuronxcc-2.17.194.0+d312836f/MODULE_c4eacc972a112955fd4c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
7902
  neuronxcc-2.17.194.0+d312836f/MODULE_d1a07b3f87341b20d662+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7903
  neuronxcc-2.17.194.0+d312836f/MODULE_7d5018ab15d06798796c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7904
  neuronxcc-2.17.194.0+d312836f/MODULE_c4eacc972a112955fd4c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
7905
+ neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/model.neff filter=lfs diff=lfs merge=lfs -text
7906
+ neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7907
+ neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/model.neff filter=lfs diff=lfs merge=lfs -text
7908
+ neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/model.neff filter=lfs diff=lfs merge=lfs -text
7909
+ neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.neff filter=lfs diff=lfs merge=lfs -text
7910
+ neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7911
+ neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.neff filter=lfs diff=lfs merge=lfs -text
7912
+ neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/model.neff filter=lfs diff=lfs merge=lfs -text
7913
+ neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
7914
+ neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
7915
+ neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
7916
+ neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev4/mixtral/dacorvo/Mixtral-tiny/3bd58a8f29b6ca08f6a0.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "dacorvo/Mixtral-tiny",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "MixtralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3584,
14
+ "max_position_embeddings": 1024,
15
+ "model_type": "mixtral",
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": "dacorvo/Mixtral-tiny",
24
+ "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
25
+ "ctx_batch_size": 2,
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
+ "is_continuous_batching": false,
33
+ "local_ranks_size": 2,
34
+ "logical_nc_config": 1,
35
+ "max_batch_size": 2,
36
+ "max_context_length": 100,
37
+ "max_topk": 256,
38
+ "mlp_kernel_enabled": false,
39
+ "mlp_kernel_fuse_residual_add": false,
40
+ "n_active_tokens": 100,
41
+ "neuronxcc_version": "2.17.194.0+d312836f",
42
+ "num_cores_per_group": 1,
43
+ "on_device_sampling": false,
44
+ "optimum_neuron_version": "0.2.0.dev4",
45
+ "output_logits": false,
46
+ "padding_side": "right",
47
+ "pp_degree": 1,
48
+ "qk_layernorm": false,
49
+ "qkv_kernel_enabled": false,
50
+ "rpl_reduce_dtype": "float16",
51
+ "sequence_length": 100,
52
+ "sequence_parallel_enabled": false,
53
+ "speculation_length": 0,
54
+ "start_rank_id": 0,
55
+ "target": null,
56
+ "tkg_batch_size": 2,
57
+ "torch_dtype": "float16",
58
+ "tp_degree": 2,
59
+ "vocab_parallel": false
60
+ },
61
+ "num_attention_heads": 32,
62
+ "num_experts_per_tok": 2,
63
+ "num_hidden_layers": 2,
64
+ "num_key_value_heads": 8,
65
+ "num_local_experts": 8,
66
+ "output_router_logits": false,
67
+ "rms_norm_eps": 1e-05,
68
+ "rope_theta": 10000.0,
69
+ "router_aux_loss_coef": 0.001,
70
+ "router_jitter_noise": 0.0,
71
+ "sliding_window": 4096,
72
+ "tie_word_embeddings": false,
73
+ "use_cache": true,
74
+ "vocab_size": 32000
75
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev4/mixtral/dacorvo/Mixtral-tiny/605773b6644d01e65e12.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "dacorvo/Mixtral-tiny",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "MixtralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3584,
14
+ "max_position_embeddings": 1024,
15
+ "model_type": "mixtral",
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": "dacorvo/Mixtral-tiny",
24
+ "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
25
+ "ctx_batch_size": 1,
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
+ "is_continuous_batching": false,
33
+ "local_ranks_size": 2,
34
+ "logical_nc_config": 1,
35
+ "max_batch_size": 1,
36
+ "max_context_length": 100,
37
+ "max_topk": 256,
38
+ "mlp_kernel_enabled": false,
39
+ "mlp_kernel_fuse_residual_add": false,
40
+ "n_active_tokens": 100,
41
+ "neuronxcc_version": "2.17.194.0+d312836f",
42
+ "num_cores_per_group": 1,
43
+ "on_device_sampling": false,
44
+ "optimum_neuron_version": "0.2.0.dev4",
45
+ "output_logits": false,
46
+ "padding_side": "right",
47
+ "pp_degree": 1,
48
+ "qk_layernorm": false,
49
+ "qkv_kernel_enabled": false,
50
+ "rpl_reduce_dtype": "float16",
51
+ "sequence_length": 100,
52
+ "sequence_parallel_enabled": false,
53
+ "speculation_length": 0,
54
+ "start_rank_id": 0,
55
+ "target": null,
56
+ "tkg_batch_size": 1,
57
+ "torch_dtype": "float16",
58
+ "tp_degree": 2,
59
+ "vocab_parallel": false
60
+ },
61
+ "num_attention_heads": 32,
62
+ "num_experts_per_tok": 2,
63
+ "num_hidden_layers": 2,
64
+ "num_key_value_heads": 8,
65
+ "num_local_experts": 8,
66
+ "output_router_logits": false,
67
+ "rms_norm_eps": 1e-05,
68
+ "rope_theta": 10000.0,
69
+ "router_aux_loss_coef": 0.001,
70
+ "router_jitter_noise": 0.0,
71
+ "sliding_window": 4096,
72
+ "tie_word_embeddings": false,
73
+ "use_cache": true,
74
+ "vocab_size": 32000
75
+ }
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev4/mixtral/dacorvo/Mixtral-tiny/78dc7e071d7a0e3aef78.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "dacorvo/Mixtral-tiny",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "MixtralForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "head_dim": 32,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3584,
14
+ "max_position_embeddings": 1024,
15
+ "model_type": "mixtral",
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": "dacorvo/Mixtral-tiny",
24
+ "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
25
+ "ctx_batch_size": 1,
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
+ "is_continuous_batching": false,
33
+ "local_ranks_size": 2,
34
+ "logical_nc_config": 1,
35
+ "max_batch_size": 1,
36
+ "max_context_length": 100,
37
+ "max_topk": 256,
38
+ "mlp_kernel_enabled": false,
39
+ "mlp_kernel_fuse_residual_add": false,
40
+ "n_active_tokens": 100,
41
+ "neuronxcc_version": "2.17.194.0+d312836f",
42
+ "num_cores_per_group": 1,
43
+ "on_device_sampling": false,
44
+ "optimum_neuron_version": "0.2.0.dev4",
45
+ "output_logits": false,
46
+ "padding_side": "right",
47
+ "pp_degree": 1,
48
+ "qk_layernorm": false,
49
+ "qkv_kernel_enabled": false,
50
+ "rpl_reduce_dtype": "bfloat16",
51
+ "sequence_length": 100,
52
+ "sequence_parallel_enabled": false,
53
+ "speculation_length": 0,
54
+ "start_rank_id": 0,
55
+ "target": null,
56
+ "tkg_batch_size": 1,
57
+ "torch_dtype": "bfloat16",
58
+ "tp_degree": 2,
59
+ "vocab_parallel": false
60
+ },
61
+ "num_attention_heads": 32,
62
+ "num_experts_per_tok": 2,
63
+ "num_hidden_layers": 2,
64
+ "num_key_value_heads": 8,
65
+ "num_local_experts": 8,
66
+ "output_router_logits": false,
67
+ "rms_norm_eps": 1e-05,
68
+ "rope_theta": 10000.0,
69
+ "router_aux_loss_coef": 0.001,
70
+ "router_jitter_noise": 0.0,
71
+ "sliding_window": 4096,
72
+ "tie_word_embeddings": false,
73
+ "use_cache": true,
74
+ "vocab_size": 32000
75
+ }
neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --internal-enable-dge-levels vector_dynamic_offsets --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14d5d4503b847582f151a502987322ecff79bf509b56a85ae3e8ee6eced9eb3d
3
+ size 70331
neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835643c604e16b2ec92cbc827fbed3ba52377952e4f43a03f0ef477fab2be58a
3
+ size 257024
neuronxcc-2.17.194.0+d312836f/MODULE_003eca68b53533d6f2a7+bfc62e4c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8beb07fd571dcb70c6a4cadbbcce768d8767ca444a2e0091196009bf8f8292e8
3
+ size 268322
neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --internal-enable-dge-levels vector_dynamic_offsets --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79d04d70742e352fb835ada4d3f0d1a478e4d28d60f41c27e1299b8ea63f1fec
3
+ size 81317
neuronxcc-2.17.194.0+d312836f/MODULE_54cb17f251d5b78afb71+26ac6be0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97c0d85272d6d6e24f01e06ea55c38562035f95e4a8283cd7f81e96097b3d8b1
3
+ size 359424
neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --internal-enable-dge-levels vector_dynamic_offsets --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05707845146df151ef6994ed3053691c7d6c6ac0d2b76b0ca998f910f197b9a6
3
+ size 81319
neuronxcc-2.17.194.0+d312836f/MODULE_5c17a6fec29c60d2f8a5+26ac6be0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e4c464344eb87216f5062358da12ad2944eafcc04a9ccca002af25f5dc55295
3
+ size 359424
neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --internal-enable-dge-levels vector_dynamic_offsets --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f71737f6ba0cf30a1390228ae07d8b66e24511de80060bfdeb9681627e258714
3
+ size 81486
neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301a92fbee06b6cc0a6021a0f3971876885e894feb84134dee23330484df95ed
3
+ size 318464
neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7355e73d423890bb78057da1083c86320b3d4f862d2e6456f9914d9b0b267a14
3
+ size 329762
neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --internal-enable-dge-levels vector_dynamic_offsets --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:420670e90420f71cc3b79c9680ccf8db2d2d3cb005ab48b09b9b70be64ce1736
3
+ size 82168
neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01d76404fcf0d7565b068d4d3f3ad427e2772eb8fd793b70381263a008d6fd25
3
+ size 420864
neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ "--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --internal-enable-dge-levels vector_dynamic_offsets --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e907b258e31ef2e3c528e49ac42f8c52ff113304ea247c87fc3f28b86f45e9e
3
+ size 70333
neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ed0fa356ea7c181eadc8397443a5dc04383c01ce73cba7d172bfd24aef3712e
3
+ size 257024
neuronxcc-2.17.194.0+d312836f/MODULE_79b0456da25f2c0f8717+bfc62e4c/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:626a30dd2f705a00518e54129b78294d5a90fdba334a1d47b3000e0d9f79dd1c
3
+ size 268322
neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+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_a605ff8b35de0a052bdc+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae3e43101a6f8c8ab9135a5cfc2cff49caddf260e15046733c0c73482dc59c89
3
+ size 11183
neuronxcc-2.17.194.0+d312836f/MODULE_a605ff8b35de0a052bdc+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c8cfa30309f10351db25c4736ce9b87b0fdca32d764974f3c8b7256b2c97ac
3
+ size 103424
neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+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_bc5c4a3dc3793311bdff+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdeb2e4320275e963f7c04a32fbcfb1e04e36ae16f278bd321f26f72de371d50
3
+ size 11183
neuronxcc-2.17.194.0+d312836f/MODULE_bc5c4a3dc3793311bdff+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:837f830d4fd5e341492e54b4c9a6a848d5b6e796cfec560a121308ebfe1aaed0
3
+ size 103424
neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+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_bfedca8ab047e39c175b+431f5505/model.done ADDED
File without changes
neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7db2a378cf8ef5084513f66b3c81c0e91b383adaf4569dca7e3e2a39901244
3
+ size 11183
neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cac7b72ccc170f7d3c7ecf3395323f73bb336f90f5c9a351b43904b7b9cf462f
3
+ size 103424