Synchronizing local compiler cache.
Browse files- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev2/qwen3/Qwen/Qwen3-0.6B/2ed7a8812dbe9c7ab058.json +101 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c6882381e4240eeeb0c+431f5505/model.neff +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_20ce63f489314924a057+253d6470/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_20ce63f489314924a057+253d6470/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d2de0754e92d084bfdd+431f5505/model.neff +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_64f5633fb25cfe2548d6+253d6470/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_64f5633fb25cfe2548d6+253d6470/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_806ef7cec3a07d99b574+cd3419b6/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_806ef7cec3a07d99b574+cd3419b6/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ace0c273811c44dd64c1+431f5505/model.neff +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_b522f7aabb6b091bde5f+253d6470/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_b522f7aabb6b091bde5f+253d6470/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_df21c2b35cb01f251b78+cd3419b6/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_df21c2b35cb01f251b78+cd3419b6/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_f561bf7d12efdc67186d+cd3419b6/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_f561bf7d12efdc67186d+cd3419b6/wrapped_neff.hlo +1 -1
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev2/qwen3/Qwen/Qwen3-0.6B/2ed7a8812dbe9c7ab058.json
ADDED
|
@@ -0,0 +1,101 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen3-0.6B",
|
| 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": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_types": [
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention"
|
| 44 |
+
],
|
| 45 |
+
"max_position_embeddings": 40960,
|
| 46 |
+
"max_window_layers": 28,
|
| 47 |
+
"model_type": "qwen3",
|
| 48 |
+
"neuron": {
|
| 49 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 50 |
+
"async_mode": false,
|
| 51 |
+
"attn_kernel_enabled": false,
|
| 52 |
+
"batch_size": 4,
|
| 53 |
+
"capacity_factor": null,
|
| 54 |
+
"cc_pipeline_tiling_factor": 2,
|
| 55 |
+
"checkpoint_id": "Qwen/Qwen3-0.6B",
|
| 56 |
+
"checkpoint_revision": "c1899de289a04d12100db370d81485cdf75e47ca",
|
| 57 |
+
"continuous_batching": true,
|
| 58 |
+
"enable_bucketing": false,
|
| 59 |
+
"ep_degree": 1,
|
| 60 |
+
"flash_decoding_enabled": false,
|
| 61 |
+
"fused_qkv": true,
|
| 62 |
+
"glu_mlp": true,
|
| 63 |
+
"is_chunked_prefill": false,
|
| 64 |
+
"local_ranks_size": 2,
|
| 65 |
+
"logical_nc_config": 1,
|
| 66 |
+
"max_batch_size": 4,
|
| 67 |
+
"max_context_length": 4096,
|
| 68 |
+
"max_topk": 256,
|
| 69 |
+
"mlp_kernel_enabled": false,
|
| 70 |
+
"mlp_kernel_fuse_residual_add": false,
|
| 71 |
+
"n_active_tokens": 4096,
|
| 72 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
| 73 |
+
"num_cores_per_group": 1,
|
| 74 |
+
"on_device_sampling": false,
|
| 75 |
+
"optimum_neuron_version": "0.3.1.dev2",
|
| 76 |
+
"output_logits": false,
|
| 77 |
+
"padding_side": "right",
|
| 78 |
+
"pp_degree": 1,
|
| 79 |
+
"qkv_kernel_enabled": false,
|
| 80 |
+
"rpl_reduce_dtype": "bfloat16",
|
| 81 |
+
"sequence_length": 4096,
|
| 82 |
+
"sequence_parallel_enabled": false,
|
| 83 |
+
"speculation_length": 0,
|
| 84 |
+
"start_rank_id": 0,
|
| 85 |
+
"target": null,
|
| 86 |
+
"torch_dtype": "bfloat16",
|
| 87 |
+
"tp_degree": 2,
|
| 88 |
+
"vocab_parallel": false
|
| 89 |
+
},
|
| 90 |
+
"num_attention_heads": 16,
|
| 91 |
+
"num_hidden_layers": 28,
|
| 92 |
+
"num_key_value_heads": 8,
|
| 93 |
+
"rms_norm_eps": 1e-06,
|
| 94 |
+
"rope_scaling": null,
|
| 95 |
+
"rope_theta": 1000000,
|
| 96 |
+
"sliding_window": null,
|
| 97 |
+
"tie_word_embeddings": true,
|
| 98 |
+
"use_cache": true,
|
| 99 |
+
"use_sliding_window": false,
|
| 100 |
+
"vocab_size": 151936
|
| 101 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c6882381e4240eeeb0c+431f5505/model.neff
CHANGED
|
Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c6882381e4240eeeb0c+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_1c6882381e4240eeeb0c+431f5505/model.neff differ
|
|
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_20ce63f489314924a057+253d6470/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 63331
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85309e8d8a9287b1f88c6d846768a98cc6a4f616cfb752b5832b6c694932cf16
|
| 3 |
size 63331
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_20ce63f489314924a057+253d6470/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 287744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aaa865d187f382cac151d6a4fa0507538ff86f33c01016502dfbb9ab1d3dcb35
|
| 3 |
size 287744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d2de0754e92d084bfdd+431f5505/model.neff
CHANGED
|
Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d2de0754e92d084bfdd+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_2d2de0754e92d084bfdd+431f5505/model.neff differ
|
|
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_64f5633fb25cfe2548d6+253d6470/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 63330
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59673436e195ca901d421e7fcdc9fb477883be70bd795b9921122b1ee14bbe81
|
| 3 |
size 63330
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_64f5633fb25cfe2548d6+253d6470/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 287744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:668ffe832ecfc69ae7116bbcc03a8ae993521c733c7706d72dc3347cce2f231b
|
| 3 |
size 287744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_806ef7cec3a07d99b574+cd3419b6/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 287744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4706a31dbd186202d3d9478e87801604fa4d625e8fe27d04b56707e618308121
|
| 3 |
size 287744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_806ef7cec3a07d99b574+cd3419b6/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 297990
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2a77ec3502f1050cd4c277aed7fd1f017e182725935b999aed00ad18a811f3e
|
| 3 |
size 297990
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ace0c273811c44dd64c1+431f5505/model.neff
CHANGED
|
Binary files a/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ace0c273811c44dd64c1+431f5505/model.neff and b/neuronxcc-2.19.8089.0+8ab9f450/MODULE_ace0c273811c44dd64c1+431f5505/model.neff differ
|
|
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_b522f7aabb6b091bde5f+253d6470/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 63921
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:984ddaf17ca6a7c663dc482b04d7a8a2c0393924610a68d11069167e061209e5
|
| 3 |
size 63921
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_b522f7aabb6b091bde5f+253d6470/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:25ce78de26c967a212d957bd316cdd70f46ab9a374b7e518a6d0b6d35e598d78
|
| 3 |
size 267264
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_df21c2b35cb01f251b78+cd3419b6/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 277504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:395c3cce7a5213d3f1c9d188935dd7a775ee28e10d52f06f790f04e3618cc27b
|
| 3 |
size 277504
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_df21c2b35cb01f251b78+cd3419b6/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 287750
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3ff6b604d0a08cbe7d6648b37bc949e551a3c8518c2f2dfb347f6afbb09a584
|
| 3 |
size 287750
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f561bf7d12efdc67186d+cd3419b6/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 287744
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:120a68f240eafcf169cd0580fd34273cec54cba40dbeee07e80091000787a9ff
|
| 3 |
size 287744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f561bf7d12efdc67186d+cd3419b6/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 297990
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a974016e8cddfb08eea5e047de22dde963c3c1fe89eeedd6805007b5252f0679
|
| 3 |
size 297990
|