Synchronizing local compiler cache.
Browse files- neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/a070bcebf3c2bb1b7d11.json +83 -0
- neuronxcc-2.26.6360.0+6f180f47/MODULE_31f800285afef122700a+519f203d/model.neff +2 -2
- neuronxcc-2.26.6360.0+6f180f47/MODULE_51bdae28051bc87badd5+84337dd9/model.neff +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_51bdae28051bc87badd5+84337dd9/wrapped_neff.hlo +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_5459e3e60c7ca34be52b+84337dd9/model.neff +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_5459e3e60c7ca34be52b+84337dd9/wrapped_neff.hlo +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_813c4591c1c397fa42bc+84337dd9/model.neff +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_813c4591c1c397fa42bc+84337dd9/wrapped_neff.hlo +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_ca940b5929c96ea4ebad+12dd9119/model.neff +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/model.neff +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/wrapped_neff.hlo +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_dc04527b827075028b3a+519f203d/model.neff +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_f9dd548904a4ef181037+12dd9119/model.hlo_module.pb +1 -1
- neuronxcc-2.26.6360.0+6f180f47/MODULE_f9dd548904a4ef181037+12dd9119/model.neff +1 -1
neuronxcc-2.26.6360.0+6f180f47/0_REGISTRY/0.4.7/4cb7aff9e2a15c151396f2b684013e39d6739f0dec83e5c9dabbfe9d5fcf77b7/a070bcebf3c2bb1b7d11.json
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "Qwen/Qwen2.5-0.5B",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"Qwen2ForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"dtype": "bfloat16",
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 896,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 4864,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 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 |
+
],
|
| 40 |
+
"max_position_embeddings": 32768,
|
| 41 |
+
"max_window_layers": 24,
|
| 42 |
+
"model_type": "qwen2",
|
| 43 |
+
"neuron": {
|
| 44 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 45 |
+
"batch_size": 1,
|
| 46 |
+
"capacity_factor": null,
|
| 47 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
| 48 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
| 49 |
+
"continuous_batching": false,
|
| 50 |
+
"ep_degree": 1,
|
| 51 |
+
"fused_qkv": false,
|
| 52 |
+
"glu_mlp": true,
|
| 53 |
+
"local_ranks_size": 2,
|
| 54 |
+
"max_batch_size": 1,
|
| 55 |
+
"max_context_length": 8192,
|
| 56 |
+
"max_topk": 256,
|
| 57 |
+
"n_active_tokens": 8192,
|
| 58 |
+
"neuronxcc_version": "2.26.6360.0+6f180f47",
|
| 59 |
+
"on_device_sampling": true,
|
| 60 |
+
"optimum_neuron_version": "0.4.7",
|
| 61 |
+
"output_logits": false,
|
| 62 |
+
"pp_degree": 1,
|
| 63 |
+
"prefill_chunk_size": 1024,
|
| 64 |
+
"sequence_length": 8192,
|
| 65 |
+
"speculation_length": 0,
|
| 66 |
+
"start_rank_id": 0,
|
| 67 |
+
"target": "trn1",
|
| 68 |
+
"torch_dtype": "bfloat16",
|
| 69 |
+
"tp_degree": 2
|
| 70 |
+
},
|
| 71 |
+
"num_attention_heads": 14,
|
| 72 |
+
"num_hidden_layers": 24,
|
| 73 |
+
"num_key_value_heads": 2,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_scaling": null,
|
| 76 |
+
"rope_theta": 1000000.0,
|
| 77 |
+
"sliding_window": null,
|
| 78 |
+
"tie_word_embeddings": true,
|
| 79 |
+
"use_cache": true,
|
| 80 |
+
"use_mrope": false,
|
| 81 |
+
"use_sliding_window": false,
|
| 82 |
+
"vocab_size": 151936
|
| 83 |
+
}
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_31f800285afef122700a+519f203d/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30dbdddc510010c02caa7e4d8005fb3125d7fe04338c7cffcf81d15e1226e042
|
| 3 |
+
size 3216384
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_51bdae28051bc87badd5+84337dd9/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1588224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c726878cf0fb176f1bd72c76c5df4006608b2f92fd8ac96bffa0bb2943af003a
|
| 3 |
size 1588224
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_51bdae28051bc87badd5+84337dd9/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1744530
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d90d8d6eaf5cfb02674773cbe8077b40c9cc288c7cec4ed5d1ea1b6ed6687c30
|
| 3 |
size 1744530
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_5459e3e60c7ca34be52b+84337dd9/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1547264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc7f1f16e738148da0ad40ffd6e8e9ce4a3eb8303549968ddaaaa7e4ee2921d4
|
| 3 |
size 1547264
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_5459e3e60c7ca34be52b+84337dd9/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1703455
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:475a88e21367427ad9b691c04ad2913424083143959ce2642d852c03eb0dfa31
|
| 3 |
size 1703455
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_813c4591c1c397fa42bc+84337dd9/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2161664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b5b0ad23250795560eb46b65f81ea4d40e7605ec3757ac36042abfe20f718a3
|
| 3 |
size 2161664
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_813c4591c1c397fa42bc+84337dd9/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2235751
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:048569c61bdc1d0d139e2840859e928d6c0e6ebe17793cf719079ef2cd1ab930
|
| 3 |
size 2235751
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_ca940b5929c96ea4ebad+12dd9119/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 10261504
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6550756bc53826f9f3918843f7f8b7e1b19e0bdbe3d8c145500060c44d7287da
|
| 3 |
size 10261504
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2110464
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60fc849ebed8542f68c2bc0fb3b4e7af21d22b7ff9e0af22d4c86977c2cd6be5
|
| 3 |
size 2110464
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_cef50dd7a142db2bfa48+84337dd9/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2184663
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c775d6f64d7854903d53d94a043ca2ae523192e7d45118b956935d48ce058197
|
| 3 |
size 2184663
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_dc04527b827075028b3a+519f203d/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3062784
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:48b34f34b9e356e9450669c356d13f8c58dd2e9a1a5eb634b28367c2c4624b96
|
| 3 |
size 3062784
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_f9dd548904a4ef181037+12dd9119/model.hlo_module.pb
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 827306
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88986767c66dbe283b3b6c664d0d5f14f66598ab0a23e7cb1258d5e5aedb92c8
|
| 3 |
size 827306
|
neuronxcc-2.26.6360.0+6f180f47/MODULE_f9dd548904a4ef181037+12dd9119/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14593024
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e039d700cb5dadda8a63ea4d5b44122dd357926afc168039caedf4b3f4342106
|
| 3 |
size 14593024
|