Synchronizing local compiler cache.
Browse files- .gitattributes +4 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/meta-llama/Llama-2-13b-hf/f0add86a079d9067a2dd.json +71 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+431f5505/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+431f5505/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+431f5505/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+431f5505/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.hlo_module.pb +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/model.neff +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/wrapped_neff.hlo +1 -1
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/wrapped_neff.hlo +3 -0
.gitattributes
CHANGED
@@ -9579,3 +9579,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_37b42d1bc5acf9f02345+a9d440f5/model.neff f
|
|
9579 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_37b42d1bc5acf9f02345+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
9580 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_be0b89d6c02ad6b4f0cd+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
9581 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f524cf812b13b8f4715d+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
9579 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_37b42d1bc5acf9f02345+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
9580 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_be0b89d6c02ad6b4f0cd+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
9581 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f524cf812b13b8f4715d+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
9582 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
9583 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
9584 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
9585 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/llama/meta-llama/Llama-2-13b-hf/f0add86a079d9067a2dd.json
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "meta-llama/Llama-2-13b-hf",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"LlamaForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_bias": false,
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"head_dim": 128,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 5120,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 13824,
|
15 |
+
"max_position_embeddings": 4096,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
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": "meta-llama/Llama-2-13b-hf",
|
26 |
+
"checkpoint_revision": "5c31dfb671ce7cfe2d7bb7c04375e44c55e815b1",
|
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": 8,
|
35 |
+
"logical_nc_config": 1,
|
36 |
+
"max_batch_size": 1,
|
37 |
+
"max_context_length": 2048,
|
38 |
+
"max_topk": 256,
|
39 |
+
"mlp_kernel_enabled": false,
|
40 |
+
"mlp_kernel_fuse_residual_add": false,
|
41 |
+
"n_active_tokens": 2048,
|
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": 2048,
|
53 |
+
"sequence_parallel_enabled": false,
|
54 |
+
"speculation_length": 0,
|
55 |
+
"start_rank_id": 0,
|
56 |
+
"target": null,
|
57 |
+
"torch_dtype": "bfloat16",
|
58 |
+
"tp_degree": 8,
|
59 |
+
"vocab_parallel": false
|
60 |
+
},
|
61 |
+
"num_attention_heads": 40,
|
62 |
+
"num_hidden_layers": 40,
|
63 |
+
"num_key_value_heads": 40,
|
64 |
+
"pretraining_tp": 1,
|
65 |
+
"rms_norm_eps": 1e-05,
|
66 |
+
"rope_scaling": null,
|
67 |
+
"rope_theta": 10000.0,
|
68 |
+
"tie_word_embeddings": false,
|
69 |
+
"use_cache": true,
|
70 |
+
"vocab_size": 32000
|
71 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.hlo_module.pb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 947655
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce8ab69c78f9087ad35e56c2f49ab70442de201a04a36e6c0557177a7165ec71
|
3 |
size 947655
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_09f4395a4e006c5aab17+ed72d204/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31130624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:206f0245d8735f1169a6a8bd482d3e9bc577903f4e9634beaa8c01b4af168750
|
3 |
size 31130624
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+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_157cb3e1c520283f8243+431f5505/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+431f5505/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6335a313295603c4f28fd60d67bfeb8a7c960da50bdb3de7e07d0cbebcc988cd
|
3 |
+
size 170955
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_157cb3e1c520283f8243+431f5505/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24e657cf019b54d60d5432f5a554175822ad56361e9f458303634e5b8f76a407
|
3 |
+
size 4271104
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4946944
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:824e2d358a46e0c593ebe16d70ddc00a08bf3186c3a7a9670cc2f58e05aa5c42
|
3 |
size 4946944
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_40c6949869ebcdeedaf2+a9d440f5/wrapped_neff.hlo
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5084761
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37fa2e5c594e7f4b0947d35e59a24754e7df7dda50abd661be92613cd2c33a5c
|
3 |
size 5084761
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.hlo_module.pb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 947655
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee09cca30c07d9ea1951888ffe1b317eeb335d6879e9d9a4470f07b1105d87cc
|
3 |
size 947655
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_4a990475959a54a127e7+ed72d204/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31130624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0567e22a05f623f75ca2fbee70a1a823dd90c5a34bd54a23ce0ad8dd76daee5e
|
3 |
size 31130624
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3144704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b137e3e7e9461d21dae4b107a9d66542860e3ec5f0d9766890aa2c705fef9e1
|
3 |
size 3144704
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_977a8cb77ae104c74f77+a9d440f5/wrapped_neff.hlo
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3282521
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38c4faa0a5dcd29db15650b3f433c30d0743e07ea21103363a9efd6074fbb77c
|
3 |
size 3282521
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+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_9ba781a35cf54a40ce5b+ed72d204/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+ed72d204/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed0916addead7911741ca22d86a14c6a2755a1f22b4d9454f8ce7cc0a3fc0d5d
|
3 |
+
size 774686
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba781a35cf54a40ce5b+ed72d204/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:86864eb773d8fcc0f5fc814568ec2ac75aaedd4a4ad574f4b86d4a9a07f78de6
|
3 |
+
size 24914944
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2509824
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b6724b129b0e15a1e673b51eb5d54aeff8e3144f8454ff38d0d1e9db9b51af9
|
3 |
size 2509824
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a04897f50446b5fc1ea6+a9d440f5/wrapped_neff.hlo
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2647641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c525fea5f0439318b60a4000ca1900953b4067372cfa9d227b9cbf68a48be01
|
3 |
size 2647641
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.hlo_module.pb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 947655
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddd2bd03b7f66fad32a7ff8b73ce79dcf3f3fb1c0fe43738b0727a3f9795e5e9
|
3 |
size 947655
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a05cd854c08da3538898+ed72d204/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 31130624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7324a3984c27b378f15f9b5d25582b13337e8c6e70f949037e632227d903a2b4
|
3 |
size 31130624
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3871744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f83c4ed87974ffd31d164af2afe5004dd61d332e3a791d11b3450b67202b214
|
3 |
size 3871744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ac55c1189dc65c1bb9b9+a9d440f5/wrapped_neff.hlo
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4009561
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:382320cc53e615a1b32fbe2309839e198a1d90a8e99e5d186ef04d61060365a5
|
3 |
size 4009561
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+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_d646bac35d883023e597+a9d440f5/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b9627841633e83e0655717b42ee81951b03e5f51d3e198ad0ec4cec0db7363d
|
3 |
+
size 861362
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e64c34de65d0c1403ff6efb2fe95b8ef89f1bde563a8c0475d723ae1789f49c7
|
3 |
+
size 3912704
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d646bac35d883023e597+a9d440f5/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0155187cc58849bf818ce5a86e30389493d0b7a97ae83fb952c7c0f11f2fcb76
|
3 |
+
size 4085497
|