Hugging Face's logo

optimum-internal-testing
/
neuron-testing-cache

Model card Files Community
optimum-internal-testing-user commited on
Commit
2c7726f
·
verified ·
1 Parent(s): 0884006

Synchronizing local compiler cache.

Browse files
Files changed (21) hide show
  1. .gitattributes +6 -0
  2. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama4_text/tiny-random/llama-4/a5c0e784e4c447cdc8db.json +82 -0
  3. neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/b589377e2b2d4af339d9.json +66 -0
  4. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/compile_flags.json +1 -0
  5. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/model.done +0 -0
  6. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/model.hlo_module.pb +3 -0
  7. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/model.neff +3 -0
  8. neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/wrapped_neff.hlo +3 -0
  9. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/compile_flags.json +1 -0
  10. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/model.done +0 -0
  11. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/model.hlo_module.pb +3 -0
  12. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/model.neff +3 -0
  13. neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/wrapped_neff.hlo +3 -0
  14. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/compile_flags.json +1 -0
  15. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/model.done +0 -0
  16. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/model.hlo_module.pb +3 -0
  17. neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/model.neff +3 -0
  18. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/compile_flags.json +1 -0
  19. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/model.done +0 -0
  20. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/model.hlo_module.pb +3 -0
  21. neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/model.neff +3 -0
.gitattributes CHANGED
@@ -4910,3 +4910,9 @@ neuronxcc-2.20.9961.0+0acef03a/MODULE_c00e7fac6ed86bc91569+06a9597e/model.neff f
4910
  neuronxcc-2.20.9961.0+0acef03a/MODULE_c00e7fac6ed86bc91569+06a9597e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4911
  neuronxcc-2.20.9961.0+0acef03a/MODULE_ec44ea5182823b6cc76d+15f50351/model.neff filter=lfs diff=lfs merge=lfs -text
4912
  neuronxcc-2.20.9961.0+0acef03a/MODULE_ec44ea5182823b6cc76d+15f50351/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
4910
  neuronxcc-2.20.9961.0+0acef03a/MODULE_c00e7fac6ed86bc91569+06a9597e/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4911
  neuronxcc-2.20.9961.0+0acef03a/MODULE_ec44ea5182823b6cc76d+15f50351/model.neff filter=lfs diff=lfs merge=lfs -text
4912
  neuronxcc-2.20.9961.0+0acef03a/MODULE_ec44ea5182823b6cc76d+15f50351/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4913
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
4914
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4915
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
4916
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
4917
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
4918
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama4_text/tiny-random/llama-4/a5c0e784e4c447cdc8db.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "tiny-random/llama-4",
4
+ "_task": "text-generation",
5
+ "attention_bias": false,
6
+ "attention_chunk_size": 128,
7
+ "attention_dropout": 0.0,
8
+ "attn_scale": 0.1,
9
+ "attn_temperature_tuning": 4,
10
+ "cache_implementation": "hybrid",
11
+ "floor_scale": 8192,
12
+ "for_llm_compressor": false,
13
+ "head_dim": 32,
14
+ "hidden_act": "silu",
15
+ "hidden_size": 32,
16
+ "initializer_range": 0.02,
17
+ "interleave_moe_layer_step": 2,
18
+ "intermediate_size": 64,
19
+ "intermediate_size_mlp": 128,
20
+ "layer_types": [
21
+ "chunked_attention",
22
+ "chunked_attention",
23
+ "chunked_attention",
24
+ "full_attention"
25
+ ],
26
+ "max_position_embeddings": 1048576,
27
+ "model_type": "llama4_text",
28
+ "moe_layers": [
29
+ 1,
30
+ 3
31
+ ],
32
+ "neuron": {
33
+ "_serialized_key": "NxDNeuronConfig",
34
+ "batch_size": 1,
35
+ "capacity_factor": null,
36
+ "checkpoint_id": "tiny-random/llama-4",
37
+ "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4",
38
+ "continuous_batching": false,
39
+ "enable_bucketing": false,
40
+ "ep_degree": 1,
41
+ "fused_qkv": false,
42
+ "glu_mlp": true,
43
+ "local_ranks_size": 2,
44
+ "logical_nc_config": 1,
45
+ "max_batch_size": 1,
46
+ "max_context_length": 1024,
47
+ "max_topk": 256,
48
+ "n_active_tokens": 1024,
49
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
50
+ "on_device_sampling": true,
51
+ "optimum_neuron_version": "0.3.1.dev6",
52
+ "output_logits": false,
53
+ "pp_degree": 1,
54
+ "sequence_length": 1024,
55
+ "speculation_length": 0,
56
+ "start_rank_id": 0,
57
+ "target": null,
58
+ "torch_dtype": "bfloat16",
59
+ "tp_degree": 2
60
+ },
61
+ "no_rope_layers": [
62
+ 1,
63
+ 1,
64
+ 1,
65
+ 0
66
+ ],
67
+ "num_attention_heads": 1,
68
+ "num_experts_per_tok": 1,
69
+ "num_hidden_layers": 4,
70
+ "num_key_value_heads": 1,
71
+ "num_local_experts": 8,
72
+ "output_router_logits": false,
73
+ "rms_norm_eps": 1e-05,
74
+ "rope_scaling": null,
75
+ "rope_theta": 500000.0,
76
+ "router_aux_loss_coef": 0.001,
77
+ "router_jitter_noise": 0.0,
78
+ "tie_word_embeddings": true,
79
+ "use_cache": true,
80
+ "use_qk_norm": true,
81
+ "vocab_size": 202048
82
+ }
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/qwen3_moe/optimum-internal-testing/tiny-random-qwen3_moe/b589377e2b2d4af339d9.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "optimum-internal-testing/tiny-random-qwen3_moe",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen3MoeForCausalLM"
7
+ ],
8
+ "attention_bias": false,
9
+ "attention_dropout": 0.0,
10
+ "decoder_sparse_step": 2,
11
+ "head_dim": 32,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 64,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 128,
16
+ "max_position_embeddings": 40960,
17
+ "max_window_layers": 1,
18
+ "mlp_only_layers": [],
19
+ "model_type": "qwen3_moe",
20
+ "moe_intermediate_size": 128,
21
+ "neuron": {
22
+ "_serialized_key": "NxDNeuronConfig",
23
+ "batch_size": 1,
24
+ "capacity_factor": null,
25
+ "checkpoint_id": "optimum-internal-testing/tiny-random-qwen3_moe",
26
+ "checkpoint_revision": "e0230be2839556b44b7400a233c73c74b4abb7af",
27
+ "continuous_batching": false,
28
+ "enable_bucketing": false,
29
+ "ep_degree": 1,
30
+ "fused_qkv": false,
31
+ "glu_mlp": true,
32
+ "local_ranks_size": 2,
33
+ "logical_nc_config": 1,
34
+ "max_batch_size": 1,
35
+ "max_context_length": 1024,
36
+ "max_topk": 256,
37
+ "n_active_tokens": 1024,
38
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
39
+ "on_device_sampling": true,
40
+ "optimum_neuron_version": "0.3.1.dev6",
41
+ "output_logits": false,
42
+ "pp_degree": 1,
43
+ "sequence_length": 1024,
44
+ "speculation_length": 0,
45
+ "start_rank_id": 0,
46
+ "target": null,
47
+ "torch_dtype": "bfloat16",
48
+ "tp_degree": 2
49
+ },
50
+ "norm_topk_prob": true,
51
+ "num_attention_heads": 2,
52
+ "num_experts": 8,
53
+ "num_experts_per_tok": 2,
54
+ "num_hidden_layers": 2,
55
+ "num_key_value_heads": 1,
56
+ "output_router_logits": false,
57
+ "rms_norm_eps": 1e-06,
58
+ "rope_scaling": null,
59
+ "rope_theta": 1000000.0,
60
+ "router_aux_loss_coef": 0.001,
61
+ "sliding_window": null,
62
+ "tie_word_embeddings": true,
63
+ "use_cache": true,
64
+ "use_sliding_window": false,
65
+ "vocab_size": 151936
66
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/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-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0308cc5092b60074cf52430ade9fceb952f4d32b0787707f76fbb8c2469784a8
3
+ size 673885
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89691c846a814ca4742985be0cf9c7d3da961ea4756925e963a3f7da1e1a361d
3
+ size 482304
neuronxcc-2.19.8089.0+8ab9f450/MODULE_5dcac2de0d0519182993+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a733bd27cd7804f41aaa8308934f1a038d86233c07894238bdd59fdd83edba
3
+ size 500322
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f0efc2dc3476920a8ce737c0d4df3a30632ff1eb6bd476fd6106d0491e1c793
3
+ size 93384
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d6334235c5861b8f2248b1ee1d53c92dfd8931845869657c003812c50368c57
3
+ size 287744
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7f33172c8c352e3cbb45+cd3419b6/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:234f500547e03d8dbed206d3640e955ffb8fb3dc70d9cc1a22d654681a713dc2
3
+ size 296770
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/compile_flags.json ADDED
@@ -0,0 +1 @@
 
 
1
+ ["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8f97df0228ccdac8427b256fabd6789264c9d39395b542ed47ce8bcf0c14e10
3
+ size 102055
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9e7927a94b94f192b50e+253d6470/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3369d0c38953f45fae3580ec7c6a8b232d9eca634799f05a719235dd195ef09
3
+ size 308224
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/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-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d953089c3c5060f40de369b2d8601e91bb920484927098a018b2a445bc8234f
3
+ size 703978
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac66a4f380d8429e6548+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afea3ba7674930b5a4f0e6711d9fde02dea5bccac18129973780b7574d9663da
3
+ size 553984