dacorvo HF Staff commited on
Commit
3f9149d
·
verified ·
1 Parent(s): a1ba9ec

Synchronizing local compiler cache.

Browse files
.gitattributes CHANGED
@@ -9456,3 +9456,11 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_32b584132787da220a36+431f5505/model.neff f
9456
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_56c1d3af391f964319f1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
9457
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_56c1d3af391f964319f1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
9458
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_f1f5a2f5ccf8151297f3+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
9456
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_56c1d3af391f964319f1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
9457
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_56c1d3af391f964319f1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
9458
  neuronxcc-2.19.8089.0+8ab9f450/MODULE_f1f5a2f5ccf8151297f3+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
9459
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_514714104ff788240201+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
9460
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_514714104ff788240201+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
9461
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_53392ca5f25f7e71a938+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
9462
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_682b943898783bd007a0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
9463
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_89d879f69388d23e479e+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
9464
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_db36d0641992b80c1f6e+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
9465
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f74433a8b539947c0765+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
9466
+ neuronxcc-2.19.8089.0+8ab9f450/MODULE_f74433a8b539947c0765+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/qwen2/Qwen/Qwen2.5-7B-Instruct/e2f872b0c731bb66ace7.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_entry_class": "SingleModelCacheEntry",
3
+ "_model_id": "Qwen/Qwen2.5-7B-Instruct",
4
+ "_task": "text-generation",
5
+ "architectures": [
6
+ "Qwen2ForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 3584,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 18944,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 28,
15
+ "model_type": "qwen2",
16
+ "neuron": {
17
+ "_serialized_key": "NxDNeuronConfig",
18
+ "async_mode": false,
19
+ "attn_kernel_enabled": false,
20
+ "batch_size": 4,
21
+ "capacity_factor": null,
22
+ "cc_pipeline_tiling_factor": 2,
23
+ "checkpoint_id": "Qwen/Qwen2.5-7B-Instruct",
24
+ "checkpoint_revision": "a09a35458c702b33eeacc393d103063234e8bc28",
25
+ "continuous_batching": true,
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
+ "local_ranks_size": 2,
33
+ "logical_nc_config": 1,
34
+ "max_batch_size": 4,
35
+ "max_context_length": 4096,
36
+ "max_topk": 256,
37
+ "mlp_kernel_enabled": false,
38
+ "mlp_kernel_fuse_residual_add": false,
39
+ "n_active_tokens": 4096,
40
+ "neuronxcc_version": "2.19.8089.0+8ab9f450",
41
+ "num_cores_per_group": 1,
42
+ "on_device_sampling": false,
43
+ "optimum_neuron_version": "0.3.0.dev5",
44
+ "output_logits": false,
45
+ "padding_side": "right",
46
+ "pp_degree": 1,
47
+ "qk_layernorm": false,
48
+ "qkv_kernel_enabled": false,
49
+ "rpl_reduce_dtype": "bfloat16",
50
+ "sequence_length": 4096,
51
+ "sequence_parallel_enabled": false,
52
+ "speculation_length": 0,
53
+ "start_rank_id": 0,
54
+ "target": null,
55
+ "torch_dtype": "bfloat16",
56
+ "tp_degree": 2,
57
+ "vocab_parallel": false
58
+ },
59
+ "num_attention_heads": 28,
60
+ "num_hidden_layers": 28,
61
+ "num_key_value_heads": 4,
62
+ "rms_norm_eps": 1e-06,
63
+ "rope_scaling": null,
64
+ "rope_theta": 1000000.0,
65
+ "sliding_window": 131072,
66
+ "tie_word_embeddings": false,
67
+ "use_cache": true,
68
+ "use_sliding_window": false,
69
+ "vocab_size": 152064
70
+ }
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89d879f69388d23e479e+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_89d879f69388d23e479e+431f5505/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89d879f69388d23e479e+431f5505/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caedcf4ab82e4818640284f164f89c5446d575d0de01a4ef28dd57280d8b4060
3
+ size 201970
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89d879f69388d23e479e+431f5505/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883feb7eb3bc5889315c04bf558e4f93ed095a7363c23caa10da519d2a9694f4
3
+ size 6554624
neuronxcc-2.19.8089.0+8ab9f450/MODULE_db36d0641992b80c1f6e+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_db36d0641992b80c1f6e+ed72d204/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_db36d0641992b80c1f6e+ed72d204/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c40e176f988f792c2078058c80ef6b7b1f64edc0f75ac7890ef1dbb7b3816515
3
+ size 864385
neuronxcc-2.19.8089.0+8ab9f450/MODULE_db36d0641992b80c1f6e+ed72d204/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8c58cf5fde1436a265f24d1a4d625637b9c773ea5bd9e835a5e525daa322141
3
+ size 7373824
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f74433a8b539947c0765+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_f74433a8b539947c0765+a9d440f5/model.done ADDED
File without changes
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f74433a8b539947c0765+a9d440f5/model.hlo_module.pb ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce480aca8213fd524d61623c5f8af037207f26e8bed9ea97496d2f2558c5713b
3
+ size 702804
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f74433a8b539947c0765+a9d440f5/model.neff ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1c39c53677bcdd38b78952c8d6cba8546222894fbf902e8a3a48f6c768e0ac8
3
+ size 7199744
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f74433a8b539947c0765+a9d440f5/wrapped_neff.hlo ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b7c5045ddfcb350a1c20535ecb9d44059598ccac717fbaa72e18c285502c903
3
+ size 7394196