Synchronizing local compiler cache.
Browse files- .gitattributes +8 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-1.7B/58e63cf5ab2b88d0eeb3.json +72 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/wrapped_neff.hlo +3 -0
.gitattributes
CHANGED
|
@@ -9862,3 +9862,11 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e48a604c18ebf2bd0a2+a9d440f5/model.neff f
|
|
| 9862 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e48a604c18ebf2bd0a2+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 9863 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7bcd81c5415d45862c73+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9864 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_af7666ad878997185c62+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9862 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1e48a604c18ebf2bd0a2+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 9863 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_7bcd81c5415d45862c73+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9864 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_af7666ad878997185c62+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9865 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_211030c386c3fe2ad92e+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9866 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_211030c386c3fe2ad92e+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 9867 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9868 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9869 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9870 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
| 9871 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d1cbe8b086c74f447a4b+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 9872 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f84530044bc222a4fff7+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen3/Qwen/Qwen3-1.7B/58e63cf5ab2b88d0eeb3.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen3-1.7B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen3ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 6144,
|
| 15 |
+
"max_position_embeddings": 40960,
|
| 16 |
+
"max_window_layers": 28,
|
| 17 |
+
"model_type": "qwen3",
|
| 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": "Qwen/Qwen3-1.7B",
|
| 26 |
+
"checkpoint_revision": "0060bc56d46589041c1048efd1a397421b1142b5",
|
| 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": 4096,
|
| 38 |
+
"max_topk": 256,
|
| 39 |
+
"mlp_kernel_enabled": false,
|
| 40 |
+
"mlp_kernel_fuse_residual_add": false,
|
| 41 |
+
"n_active_tokens": 4096,
|
| 42 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
| 43 |
+
"num_cores_per_group": 1,
|
| 44 |
+
"on_device_sampling": true,
|
| 45 |
+
"optimum_neuron_version": "0.3.0.dev5",
|
| 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": 4096,
|
| 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": 16,
|
| 62 |
+
"num_hidden_layers": 28,
|
| 63 |
+
"num_key_value_heads": 8,
|
| 64 |
+
"rms_norm_eps": 1e-06,
|
| 65 |
+
"rope_scaling": null,
|
| 66 |
+
"rope_theta": 1000000,
|
| 67 |
+
"sliding_window": null,
|
| 68 |
+
"tie_word_embeddings": true,
|
| 69 |
+
"use_cache": true,
|
| 70 |
+
"use_sliding_window": false,
|
| 71 |
+
"vocab_size": 151936
|
| 72 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+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-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/model.done
ADDED
|
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a2d2e4a495714200ddebbe7a9221c83734a8e849dd90eccbc18e1c751cd2167
|
| 3 |
+
size 132002
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_8fd2037559c0a95b5589+431f5505/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5718fdb833c28c1eeae0df1795310434833fac61d19508b027f6a1dec4d6894a
|
| 3 |
+
size 1281024
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+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_910a0b2fe18e01964c3c+ed72d204/model.done
ADDED
|
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+ed72d204/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5537f3738586fec652d678590a88e6197d5f2406d7f4832167e422e953957232
|
| 3 |
+
size 824766
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_910a0b2fe18e01964c3c+ed72d204/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cdc38d7f989eafdf7b572ddf662f7eab58ca2d34bbcaf0303bc94b36e23539ef
|
| 3 |
+
size 35339264
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+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_95612a7799aebdf2fbbd+a9d440f5/model.done
ADDED
|
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94729607f1c4e9a5eaa37d0341222143a3d3bbc4735b5ab5981f2aec0128f801
|
| 3 |
+
size 739961
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff84f6a9f1e342626b1225a6a598685d54cd39384af28566903fe8f9018a8e73
|
| 3 |
+
size 2407424
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_95612a7799aebdf2fbbd+a9d440f5/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c00873dee1a3acdc1c4b809c8913110cbda99101aab60df32bbcb038fba82dc
|
| 3 |
+
size 2537520
|