Synchronizing local compiler cache.
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +9 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/5c73888c2d99ebb0b3e1.json +74 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/abd6677f389d97d11f17.json +74 -0
- neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b6730030a303f82cd988.json +74 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/wrapped_neff.hlo +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/wrapped_neff.hlo +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/wrapped_neff.hlo +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/wrapped_neff.hlo +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.hlo_module.pb +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.neff +1 -1
- neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.hlo_module.pb +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.neff +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/wrapped_neff.hlo +3 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/compile_flags.json +1 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done +0 -0
- neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb +3 -0
.gitattributes
CHANGED
@@ -2950,3 +2950,12 @@ neuronxcc-2.17.194.0+d312836f/MODULE_a57600b672ea2ee05d8c+165e9558/model.neff fi
|
|
2950 |
neuronxcc-2.17.194.0+d312836f/MODULE_a57600b672ea2ee05d8c+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
2951 |
neuronxcc-2.17.194.0+d312836f/MODULE_c3dda8a57464a1f8b5f3+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
|
2952 |
neuronxcc-2.17.194.0+d312836f/MODULE_f55bef5a76fbf9bf2649+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2950 |
neuronxcc-2.17.194.0+d312836f/MODULE_a57600b672ea2ee05d8c+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
2951 |
neuronxcc-2.17.194.0+d312836f/MODULE_c3dda8a57464a1f8b5f3+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
|
2952 |
neuronxcc-2.17.194.0+d312836f/MODULE_f55bef5a76fbf9bf2649+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
2953 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
|
2954 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
|
2955 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
|
2956 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
2957 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
2958 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
2959 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
2960 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
|
2961 |
+
neuronxcc-2.17.194.0+d312836f/MODULE_d8f0f9b8ac103cce2472+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/5c73888c2d99ebb0b3e1.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "yujiepan/phi-4-tiny-random",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"Phi3ForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_bias": false,
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"auto_map": {},
|
11 |
+
"embd_pdrop": 0.0,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 16,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 32,
|
16 |
+
"max_position_embeddings": 16384,
|
17 |
+
"model_type": "phi3",
|
18 |
+
"neuron": {
|
19 |
+
"_serialized_key": "NxDNeuronConfig",
|
20 |
+
"async_mode": false,
|
21 |
+
"attn_kernel_enabled": false,
|
22 |
+
"batch_size": 2,
|
23 |
+
"capacity_factor": null,
|
24 |
+
"cc_pipeline_tiling_factor": 2,
|
25 |
+
"checkpoint_id": "yujiepan/phi-4-tiny-random",
|
26 |
+
"checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
|
27 |
+
"continuous_batching": true,
|
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": 2,
|
35 |
+
"logical_nc_config": 1,
|
36 |
+
"max_batch_size": 2,
|
37 |
+
"max_context_length": 100,
|
38 |
+
"max_topk": 256,
|
39 |
+
"mlp_kernel_enabled": false,
|
40 |
+
"mlp_kernel_fuse_residual_add": false,
|
41 |
+
"n_active_tokens": 100,
|
42 |
+
"neuronxcc_version": "2.17.194.0+d312836f",
|
43 |
+
"num_cores_per_group": 1,
|
44 |
+
"on_device_sampling": false,
|
45 |
+
"optimum_neuron_version": "0.3.0.dev1",
|
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": "float16",
|
52 |
+
"sequence_length": 100,
|
53 |
+
"sequence_parallel_enabled": false,
|
54 |
+
"speculation_length": 0,
|
55 |
+
"start_rank_id": 0,
|
56 |
+
"target": null,
|
57 |
+
"torch_dtype": "float16",
|
58 |
+
"tp_degree": 2,
|
59 |
+
"vocab_parallel": false
|
60 |
+
},
|
61 |
+
"num_attention_heads": 2,
|
62 |
+
"num_hidden_layers": 2,
|
63 |
+
"num_key_value_heads": 1,
|
64 |
+
"original_max_position_embeddings": 16384,
|
65 |
+
"partial_rotary_factor": 1.0,
|
66 |
+
"resid_pdrop": 0.0,
|
67 |
+
"rms_norm_eps": 1e-05,
|
68 |
+
"rope_scaling": null,
|
69 |
+
"rope_theta": 250000,
|
70 |
+
"sliding_window": null,
|
71 |
+
"tie_word_embeddings": false,
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 100352
|
74 |
+
}
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/abd6677f389d97d11f17.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "yujiepan/phi-4-tiny-random",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"Phi3ForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_bias": false,
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"auto_map": {},
|
11 |
+
"embd_pdrop": 0.0,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 16,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 32,
|
16 |
+
"max_position_embeddings": 16384,
|
17 |
+
"model_type": "phi3",
|
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": "yujiepan/phi-4-tiny-random",
|
26 |
+
"checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
|
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": 2,
|
35 |
+
"logical_nc_config": 1,
|
36 |
+
"max_batch_size": 1,
|
37 |
+
"max_context_length": 100,
|
38 |
+
"max_topk": 256,
|
39 |
+
"mlp_kernel_enabled": false,
|
40 |
+
"mlp_kernel_fuse_residual_add": false,
|
41 |
+
"n_active_tokens": 100,
|
42 |
+
"neuronxcc_version": "2.17.194.0+d312836f",
|
43 |
+
"num_cores_per_group": 1,
|
44 |
+
"on_device_sampling": true,
|
45 |
+
"optimum_neuron_version": "0.3.0.dev1",
|
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": 100,
|
53 |
+
"sequence_parallel_enabled": false,
|
54 |
+
"speculation_length": 0,
|
55 |
+
"start_rank_id": 0,
|
56 |
+
"target": null,
|
57 |
+
"torch_dtype": "bfloat16",
|
58 |
+
"tp_degree": 2,
|
59 |
+
"vocab_parallel": false
|
60 |
+
},
|
61 |
+
"num_attention_heads": 2,
|
62 |
+
"num_hidden_layers": 2,
|
63 |
+
"num_key_value_heads": 1,
|
64 |
+
"original_max_position_embeddings": 16384,
|
65 |
+
"partial_rotary_factor": 1.0,
|
66 |
+
"resid_pdrop": 0.0,
|
67 |
+
"rms_norm_eps": 1e-05,
|
68 |
+
"rope_scaling": null,
|
69 |
+
"rope_theta": 250000,
|
70 |
+
"sliding_window": null,
|
71 |
+
"tie_word_embeddings": false,
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 100352
|
74 |
+
}
|
neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev1/phi3/yujiepan/phi-4-tiny-random/b6730030a303f82cd988.json
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "yujiepan/phi-4-tiny-random",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"Phi3ForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_bias": false,
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"auto_map": {},
|
11 |
+
"embd_pdrop": 0.0,
|
12 |
+
"hidden_act": "silu",
|
13 |
+
"hidden_size": 16,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 32,
|
16 |
+
"max_position_embeddings": 16384,
|
17 |
+
"model_type": "phi3",
|
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": "yujiepan/phi-4-tiny-random",
|
26 |
+
"checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
|
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": 2,
|
35 |
+
"logical_nc_config": 1,
|
36 |
+
"max_batch_size": 1,
|
37 |
+
"max_context_length": 100,
|
38 |
+
"max_topk": 256,
|
39 |
+
"mlp_kernel_enabled": false,
|
40 |
+
"mlp_kernel_fuse_residual_add": false,
|
41 |
+
"n_active_tokens": 100,
|
42 |
+
"neuronxcc_version": "2.17.194.0+d312836f",
|
43 |
+
"num_cores_per_group": 1,
|
44 |
+
"on_device_sampling": true,
|
45 |
+
"optimum_neuron_version": "0.3.0.dev1",
|
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": "float16",
|
52 |
+
"sequence_length": 100,
|
53 |
+
"sequence_parallel_enabled": false,
|
54 |
+
"speculation_length": 0,
|
55 |
+
"start_rank_id": 0,
|
56 |
+
"target": null,
|
57 |
+
"torch_dtype": "float16",
|
58 |
+
"tp_degree": 2,
|
59 |
+
"vocab_parallel": false
|
60 |
+
},
|
61 |
+
"num_attention_heads": 2,
|
62 |
+
"num_hidden_layers": 2,
|
63 |
+
"num_key_value_heads": 1,
|
64 |
+
"original_max_position_embeddings": 16384,
|
65 |
+
"partial_rotary_factor": 1.0,
|
66 |
+
"resid_pdrop": 0.0,
|
67 |
+
"rms_norm_eps": 1e-05,
|
68 |
+
"rope_scaling": null,
|
69 |
+
"rope_theta": 250000,
|
70 |
+
"sliding_window": null,
|
71 |
+
"tie_word_embeddings": false,
|
72 |
+
"use_cache": true,
|
73 |
+
"vocab_size": 100352
|
74 |
+
}
|
neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
"--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
|
neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:420421421ec2ed25ab59cedcabb75239718dd95a65fce87c6ac7ee15dbb3d966
|
3 |
+
size 46338
|
neuronxcc-2.17.194.0+d312836f/MODULE_0ae7505139b34db6da76+bfe5714b/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e56b5d7c2db9fb8c69e95577e2a50985f6505fcc7e8205acbf14e08a4127be01
|
3 |
+
size 144384
|
neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
"--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
|
neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d922733ac53b1bed4307a23435511e01894abdfc31f5bc4e5d103cd3b3be0287
|
3 |
+
size 79977
|
neuronxcc-2.17.194.0+d312836f/MODULE_13aef406efd76bc89e83+bfe5714b/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2ccad53a5652e6cad951ba99f5ef63025da28dade925b45bc62fc497f4f5ee8
|
3 |
+
size 205824
|
neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
"--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"
|
neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9732c88c01c966a633fb52000f3d9cfb6072c98be0e1ceb8a05f6fd748eec8e1
|
3 |
+
size 79977
|
neuronxcc-2.17.194.0+d312836f/MODULE_1ed7027480f23aac5a36+bfe5714b/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dee73b9482011a5b7b35e46d2af298c666dbafe0992bffdb4859687a5e3dcfb
|
3 |
+
size 205824
|
neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
"--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
|
neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:141f375c5586877c1c3685fd59fde284897f258fed49a5a0efc338f61fc75c07
|
3 |
+
size 46239
|
neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dd9828e87d7c1cead4fa9792f396ee54881c9acac6621e11d1a017e1b40f429
|
3 |
+
size 2325504
|
neuronxcc-2.17.194.0+d312836f/MODULE_49c7199502b64c3c4f30+165e9558/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b8871a77c65f3f73ccbc6c280a13c9670a3098c36da90766954f545a9610139
|
3 |
+
size 2333225
|
neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+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-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac612e25096c83782b4cc3de15fd519cadd414c7b094a76abf984bcbfbfc5ed3
|
3 |
+
size 7011
|
neuronxcc-2.17.194.0+d312836f/MODULE_4b0ed59c6be672048dc3+431f5505/model.neff
ADDED
Binary file (52.2 kB). View file
|
|
neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff
CHANGED
Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_4c948ba1d275cea9b124+431f5505/model.neff differ
|
|
neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.hlo_module.pb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 55929
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0384e950c159f99f387bcd7e341cd971c78baa2f71054e129b8520d91191a573
|
3 |
size 55929
|
neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2366464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b17db9e4117da233e198a40f12f7754bba35691e400b4f0d747ac2da39a44c41
|
3 |
size 2366464
|
neuronxcc-2.17.194.0+d312836f/MODULE_634439d56d5bb67e9812+165e9558/wrapped_neff.hlo
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2376747
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:428e8a01715cad356ec351df6548de386af3aa071db0736d1cd99bd99e02876a
|
3 |
size 2376747
|
neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.hlo_module.pb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 88686
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0359b0c9c36a286960b432bbc0cb0b06644300e11afc7076414cd0d5c064de15
|
3 |
size 88686
|
neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 236544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4c05973c4cf690b1269392650ca42a01ababa6fc00297ffba78bcc98b8615e3e
|
3 |
size 236544
|
neuronxcc-2.17.194.0+d312836f/MODULE_72281753d7f57952bfe4+165e9558/wrapped_neff.hlo
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 247153
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5287abba715b09dddfc465058bc5a94319e69c10c963ee4b299f1b45b2ca0b2
|
3 |
size 247153
|
neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.hlo_module.pb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 88686
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b90de1c616407583866f0da434943516bb3f67d42e167f7ca0fa4e6051802e5d
|
3 |
size 88686
|
neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 236544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b1e7c43dba8d70242622d3ad45ec0c5da34a8d40426e2ae538b373d076bab4b8
|
3 |
size 236544
|
neuronxcc-2.17.194.0+d312836f/MODULE_857bfa5db7b34c9a9421+165e9558/wrapped_neff.hlo
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 247153
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0aecb2930882f0b972a954bb1d9687f17e624d7e9255f4e69df1b08c43acfb88
|
3 |
size 247153
|
neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.hlo_module.pb
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 53519
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b23db7233e6261400ebd48aabab17a3fe541c4c354db141c216bc13ef992b639
|
3 |
size 53519
|
neuronxcc-2.17.194.0+d312836f/MODULE_94ba84f59b341a98c066+bfe5714b/model.neff
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 164864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55e8a59c82e50fe6a46ba496fd83d9a149307cdd5e722f9e14d3e5a4dc1478dc
|
3 |
size 164864
|
neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+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-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3bd2354b87e72d380a363cd1cfc99ba880da6cb454791b59fd1278345941946
|
3 |
+
size 7011
|
neuronxcc-2.17.194.0+d312836f/MODULE_9a042dec7c8f1bb9bb73+431f5505/model.neff
ADDED
Binary file (52.2 kB). View file
|
|
neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff
CHANGED
Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_9c37025554da49ae454e+431f5505/model.neff differ
|
|
neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/compile_flags.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
"--auto-cast=none --model-type=transformer --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-dge-dma --vectorize-strided-dma ' -O2 --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"
|
neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57c3b2a028e2d014aaf7892d0bcc43fdb6fdc54b9e2a6cc6734f1aab2e849f5b
|
3 |
+
size 78990
|
neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d82234a95635967ad91440355281fe9cc8e724ce0905f541466256d47e7fcba2
|
3 |
+
size 216064
|
neuronxcc-2.17.194.0+d312836f/MODULE_a4b551d188be0a834e52+165e9558/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ee5b42bf7243226b1f3ce2a062d6a6575c0eb0880f785438604d7bd129392e8
|
3 |
+
size 223770
|
neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+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-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.done
ADDED
File without changes
|
neuronxcc-2.17.194.0+d312836f/MODULE_c7b1afc8cbed0b2dbf01+431f5505/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b9e74f6e05b9bd84d59addc9f34ab7eef94e63734f2f1114b01407379ab01ac4
|
3 |
+
size 7011
|