Synchronizing local compiler cache.
Browse files- .gitattributes +4 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/a7608b4dc11bf5302b4b.json +55 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/qwen2/Qwen/Qwen2.5-0.5B/4e70c222bcc3d1952f3a.json +49 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.neff +3 -0
.gitattributes
CHANGED
@@ -2729,3 +2729,7 @@ neuronxcc-2.17.194.0+d312836f/MODULE_a76dbeab0f6653fa220b+165e9558/wrapped_neff.
|
|
2729 |
neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
2730 |
neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
2731 |
neuronxcc-2.17.194.0+d312836f/MODULE_fffbb7a74f126b7cac4f+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
2729 |
neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
2730 |
neuronxcc-2.17.194.0+d312836f/MODULE_fb9e4f974acc74d766dc+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
2731 |
neuronxcc-2.17.194.0+d312836f/MODULE_fffbb7a74f126b7cac4f+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
|
2732 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
2733 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
2734 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
2735 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/a7608b4dc11bf5302b4b.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "llamafactory/tiny-random-Llama-3",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"LlamaForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_bias": false,
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"head_dim": 4,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 16,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 64,
|
15 |
+
"max_position_embeddings": 131072,
|
16 |
+
"mlp_bias": false,
|
17 |
+
"model_type": "llama",
|
18 |
+
"neuron": {
|
19 |
+
"_serialized_key": "HloNeuronConfig",
|
20 |
+
"all_reduce_dtype": null,
|
21 |
+
"allow_flash_attention": true,
|
22 |
+
"attention_layout": "BSH",
|
23 |
+
"attn_output_transposed": false,
|
24 |
+
"auto_cast_type": "bf16",
|
25 |
+
"batch_size": 1,
|
26 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
27 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
28 |
+
"collectives_layout": "HSB",
|
29 |
+
"continuous_batching": false,
|
30 |
+
"fuse_qkv": true,
|
31 |
+
"group_query_attention": null,
|
32 |
+
"log_softmax_scores": false,
|
33 |
+
"neuronxcc_version": "2.17.194.0+d312836f",
|
34 |
+
"optimum_neuron_version": "0.2.0.dev7",
|
35 |
+
"output_all_logits": false,
|
36 |
+
"sequence_length": 131072,
|
37 |
+
"tp_degree": 2
|
38 |
+
},
|
39 |
+
"num_attention_heads": 4,
|
40 |
+
"num_hidden_layers": 2,
|
41 |
+
"num_key_value_heads": 4,
|
42 |
+
"pretraining_tp": 1,
|
43 |
+
"rms_norm_eps": 1e-05,
|
44 |
+
"rope_scaling": {
|
45 |
+
"factor": 8.0,
|
46 |
+
"high_freq_factor": 4.0,
|
47 |
+
"low_freq_factor": 1.0,
|
48 |
+
"original_max_position_embeddings": 8192,
|
49 |
+
"rope_type": "llama3"
|
50 |
+
},
|
51 |
+
"rope_theta": 500000.0,
|
52 |
+
"tie_word_embeddings": false,
|
53 |
+
"use_cache": true,
|
54 |
+
"vocab_size": 128256
|
55 |
+
}
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev7/qwen2/Qwen/Qwen2.5-0.5B/4e70c222bcc3d1952f3a.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 896,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 4864,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"max_window_layers": 24,
|
15 |
+
"model_type": "qwen2",
|
16 |
+
"neuron": {
|
17 |
+
"_serialized_key": "HloNeuronConfig",
|
18 |
+
"all_reduce_dtype": null,
|
19 |
+
"allow_flash_attention": true,
|
20 |
+
"attention_layout": "HSB",
|
21 |
+
"attn_output_transposed": false,
|
22 |
+
"auto_cast_type": "bf16",
|
23 |
+
"batch_size": 1,
|
24 |
+
"checkpoint_id": "Qwen/Qwen2.5-0.5B",
|
25 |
+
"checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
|
26 |
+
"collectives_layout": "HSB",
|
27 |
+
"continuous_batching": false,
|
28 |
+
"fuse_qkv": false,
|
29 |
+
"group_query_attention": "replicated-heads",
|
30 |
+
"log_softmax_scores": false,
|
31 |
+
"neuronxcc_version": "2.17.194.0+d312836f",
|
32 |
+
"optimum_neuron_version": "0.2.0.dev7",
|
33 |
+
"output_all_logits": false,
|
34 |
+
"sequence_length": 128,
|
35 |
+
"tp_degree": 24
|
36 |
+
},
|
37 |
+
"num_attention_heads": 14,
|
38 |
+
"num_hidden_layers": 24,
|
39 |
+
"num_key_value_heads": 2,
|
40 |
+
"rms_norm_eps": 1e-06,
|
41 |
+
"rope_scaling": null,
|
42 |
+
"rope_theta": 1000000.0,
|
43 |
+
"sliding_window": 32768,
|
44 |
+
"tie_word_embeddings": true,
|
45 |
+
"use_cache": true,
|
46 |
+
"use_mrope": false,
|
47 |
+
"use_sliding_window": false,
|
48 |
+
"vocab_size": 151936
|
49 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cbea4c84293549c875612510a0afc6d3eb7d1162da2dfa4eeb9aa9c203094d45
|
3 |
+
size 214507
|
neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35a0aa03c074f7bcd907008b6b18d4d14bbe364dd98938d7f7e114ef757780db
|
3 |
+
size 472064
|
neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b229130c77371a2a593d35bdd7958c7ce8e17d0acecd32cf976b1e3853e1f6d
|
3 |
+
size 20771
|
neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45149e7a3a20985048c681bf179c530714fcb9d5759cd136e20b1938a243e313
|
3 |
+
size 400384
|
neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15bb71673995075d87fb7b33a60286a408029ef670f778ac4c3c2d1b0eddfaf3
|
3 |
+
size 27487
|
neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1b79da8315b67f24207ac38ffc8b93434b39693e9be0b16306e94cdc5ba71b2
|
3 |
+
size 215675904
|
neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]
|
neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:18e8c33c575c8ed49e4da1d523a92d03ed72286df0ed1b6aa03b1862fb706914
|
3 |
+
size 261354
|
neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:211a60b58905bce5d4e87fc59bcf2e1e32e7395db6d7a73780cc807e48c9e274
|
3 |
+
size 461824
|