Synchronizing local compiler cache.
Browse files- .gitattributes +12 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/4042e0b5aa52d546c37f.json +63 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/4bd7f8e0c01deb46ba79.json +63 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/5882f2cc50223918592f.json +63 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/a70dd044fd7d561d10b9.json +63 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/wrapped_neff.hlo +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/wrapped_neff.hlo +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/wrapped_neff.hlo +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/wrapped_neff.hlo +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+ed72d204/model.neff +3 -0
.gitattributes
CHANGED
@@ -4580,3 +4580,15 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb945fbdfaf46f441eed+cd3419b6/model.neff f
|
|
4580 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb945fbdfaf46f441eed+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
4581 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ff4faa8edb2d2eec282d+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
|
4582 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ee7203f82f27836b9239+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4580 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_bb945fbdfaf46f441eed+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
4581 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ff4faa8edb2d2eec282d+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
|
4582 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ee7203f82f27836b9239+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
4583 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
4584 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
4585 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
4586 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
4587 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
4588 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
4589 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
4590 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
4591 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
4592 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
4593 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
4594 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/4042e0b5aa52d546c37f.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "NxDNeuronConfig",
|
20 |
+
"batch_size": 1,
|
21 |
+
"capacity_factor": null,
|
22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
24 |
+
"continuous_batching": false,
|
25 |
+
"enable_bucketing": false,
|
26 |
+
"ep_degree": 1,
|
27 |
+
"fused_qkv": true,
|
28 |
+
"glu_mlp": true,
|
29 |
+
"local_ranks_size": 2,
|
30 |
+
"logical_nc_config": 1,
|
31 |
+
"max_batch_size": 1,
|
32 |
+
"max_context_length": 512,
|
33 |
+
"max_topk": 256,
|
34 |
+
"n_active_tokens": 512,
|
35 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
36 |
+
"on_device_sampling": true,
|
37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
38 |
+
"output_logits": false,
|
39 |
+
"pp_degree": 1,
|
40 |
+
"sequence_length": 512,
|
41 |
+
"speculation_length": 0,
|
42 |
+
"start_rank_id": 0,
|
43 |
+
"target": null,
|
44 |
+
"torch_dtype": "float16",
|
45 |
+
"tp_degree": 2
|
46 |
+
},
|
47 |
+
"num_attention_heads": 4,
|
48 |
+
"num_hidden_layers": 2,
|
49 |
+
"num_key_value_heads": 4,
|
50 |
+
"pretraining_tp": 1,
|
51 |
+
"rms_norm_eps": 1e-05,
|
52 |
+
"rope_scaling": {
|
53 |
+
"factor": 8.0,
|
54 |
+
"high_freq_factor": 4.0,
|
55 |
+
"low_freq_factor": 1.0,
|
56 |
+
"original_max_position_embeddings": 8192,
|
57 |
+
"rope_type": "llama3"
|
58 |
+
},
|
59 |
+
"rope_theta": 500000.0,
|
60 |
+
"tie_word_embeddings": false,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 128256
|
63 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/4bd7f8e0c01deb46ba79.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "NxDNeuronConfig",
|
20 |
+
"batch_size": 2,
|
21 |
+
"capacity_factor": null,
|
22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
24 |
+
"continuous_batching": true,
|
25 |
+
"enable_bucketing": false,
|
26 |
+
"ep_degree": 1,
|
27 |
+
"fused_qkv": true,
|
28 |
+
"glu_mlp": true,
|
29 |
+
"local_ranks_size": 1,
|
30 |
+
"logical_nc_config": 1,
|
31 |
+
"max_batch_size": 2,
|
32 |
+
"max_context_length": 128,
|
33 |
+
"max_topk": 256,
|
34 |
+
"n_active_tokens": 128,
|
35 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
36 |
+
"on_device_sampling": true,
|
37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
38 |
+
"output_logits": false,
|
39 |
+
"pp_degree": 1,
|
40 |
+
"sequence_length": 128,
|
41 |
+
"speculation_length": 0,
|
42 |
+
"start_rank_id": 0,
|
43 |
+
"target": null,
|
44 |
+
"torch_dtype": "bfloat16",
|
45 |
+
"tp_degree": 1
|
46 |
+
},
|
47 |
+
"num_attention_heads": 4,
|
48 |
+
"num_hidden_layers": 2,
|
49 |
+
"num_key_value_heads": 4,
|
50 |
+
"pretraining_tp": 1,
|
51 |
+
"rms_norm_eps": 1e-05,
|
52 |
+
"rope_scaling": {
|
53 |
+
"factor": 8.0,
|
54 |
+
"high_freq_factor": 4.0,
|
55 |
+
"low_freq_factor": 1.0,
|
56 |
+
"original_max_position_embeddings": 8192,
|
57 |
+
"rope_type": "llama3"
|
58 |
+
},
|
59 |
+
"rope_theta": 500000.0,
|
60 |
+
"tie_word_embeddings": false,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 128256
|
63 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/5882f2cc50223918592f.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "NxDNeuronConfig",
|
20 |
+
"batch_size": 2,
|
21 |
+
"capacity_factor": null,
|
22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
24 |
+
"continuous_batching": true,
|
25 |
+
"enable_bucketing": false,
|
26 |
+
"ep_degree": 1,
|
27 |
+
"fused_qkv": true,
|
28 |
+
"glu_mlp": true,
|
29 |
+
"local_ranks_size": 2,
|
30 |
+
"logical_nc_config": 1,
|
31 |
+
"max_batch_size": 2,
|
32 |
+
"max_context_length": 128,
|
33 |
+
"max_topk": 256,
|
34 |
+
"n_active_tokens": 128,
|
35 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
36 |
+
"on_device_sampling": true,
|
37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
38 |
+
"output_logits": false,
|
39 |
+
"pp_degree": 1,
|
40 |
+
"sequence_length": 128,
|
41 |
+
"speculation_length": 0,
|
42 |
+
"start_rank_id": 0,
|
43 |
+
"target": null,
|
44 |
+
"torch_dtype": "bfloat16",
|
45 |
+
"tp_degree": 2
|
46 |
+
},
|
47 |
+
"num_attention_heads": 4,
|
48 |
+
"num_hidden_layers": 2,
|
49 |
+
"num_key_value_heads": 4,
|
50 |
+
"pretraining_tp": 1,
|
51 |
+
"rms_norm_eps": 1e-05,
|
52 |
+
"rope_scaling": {
|
53 |
+
"factor": 8.0,
|
54 |
+
"high_freq_factor": 4.0,
|
55 |
+
"low_freq_factor": 1.0,
|
56 |
+
"original_max_position_embeddings": 8192,
|
57 |
+
"rope_type": "llama3"
|
58 |
+
},
|
59 |
+
"rope_theta": 500000.0,
|
60 |
+
"tie_word_embeddings": false,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 128256
|
63 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama/llamafactory/tiny-random-Llama-3/a70dd044fd7d561d10b9.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "NxDNeuronConfig",
|
20 |
+
"batch_size": 1,
|
21 |
+
"capacity_factor": null,
|
22 |
+
"checkpoint_id": "llamafactory/tiny-random-Llama-3",
|
23 |
+
"checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
|
24 |
+
"continuous_batching": false,
|
25 |
+
"enable_bucketing": false,
|
26 |
+
"ep_degree": 1,
|
27 |
+
"fused_qkv": true,
|
28 |
+
"glu_mlp": true,
|
29 |
+
"local_ranks_size": 1,
|
30 |
+
"logical_nc_config": 1,
|
31 |
+
"max_batch_size": 1,
|
32 |
+
"max_context_length": 512,
|
33 |
+
"max_topk": 256,
|
34 |
+
"n_active_tokens": 512,
|
35 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
36 |
+
"on_device_sampling": true,
|
37 |
+
"optimum_neuron_version": "0.3.1.dev6",
|
38 |
+
"output_logits": false,
|
39 |
+
"pp_degree": 1,
|
40 |
+
"sequence_length": 512,
|
41 |
+
"speculation_length": 0,
|
42 |
+
"start_rank_id": 0,
|
43 |
+
"target": null,
|
44 |
+
"torch_dtype": "float16",
|
45 |
+
"tp_degree": 1
|
46 |
+
},
|
47 |
+
"num_attention_heads": 4,
|
48 |
+
"num_hidden_layers": 2,
|
49 |
+
"num_key_value_heads": 4,
|
50 |
+
"pretraining_tp": 1,
|
51 |
+
"rms_norm_eps": 1e-05,
|
52 |
+
"rope_scaling": {
|
53 |
+
"factor": 8.0,
|
54 |
+
"high_freq_factor": 4.0,
|
55 |
+
"low_freq_factor": 1.0,
|
56 |
+
"original_max_position_embeddings": 8192,
|
57 |
+
"rope_type": "llama3"
|
58 |
+
},
|
59 |
+
"rope_theta": 500000.0,
|
60 |
+
"tie_word_embeddings": false,
|
61 |
+
"use_cache": true,
|
62 |
+
"vocab_size": 128256
|
63 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+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_06c8dbb372e92a509892+ed72d204/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+ed72d204/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4c63a63d4f561b4fc6ea1377d3430f999ebe0df743b56092d0c3af2dee81cc1
|
3 |
+
size 81847
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_06c8dbb372e92a509892+ed72d204/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97ccfee2ee8f6b88953e50ad3be95f533c690497ca155745a86d03acf0c844b5
|
3 |
+
size 246784
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+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_0bd3d97e69c39b1f81fe+a9d440f5/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:754dac85dc7c9ebbf2b62320d22d0a7bda6c83ce940930516311115bf0dca9cb
|
3 |
+
size 74753
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:132cf771557e2993484f5217ea9b98f08e244adfd78a5a5d0b09f86bfe2b7d9d
|
3 |
+
size 308224
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_0bd3d97e69c39b1f81fe+a9d440f5/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25906d7457ccddc5ebffe556434461a7e222ecf7fd71cb060099e05cd9f90ba2
|
3 |
+
size 316031
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+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_1a52c0a90fc4f2b193c3+a9d440f5/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f5d3b10dccea6a1eec02de6e69bac32eb5630d91f157e89a094cf17435c8def
|
3 |
+
size 75228
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e64697e47cf65f8690d1768429dcb3f27a59dc878533117db2d62aa3ae3e9cea
|
3 |
+
size 287744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_1a52c0a90fc4f2b193c3+a9d440f5/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2315923d55bce245c9bb23f44f0eca66311860cc0118984556c17ec9c9dec093
|
3 |
+
size 295551
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+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_66ff57a3dcbdd1b34504+ed72d204/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+ed72d204/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d44d693804e155c576eec13b548f496b60d2bc58cb22de1c1e80a125686057da
|
3 |
+
size 86197
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_66ff57a3dcbdd1b34504+ed72d204/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65ed2eef0c7edb1c76fe30285c3c9e8ae6a3e4213abc6417231c6836412277bc
|
3 |
+
size 349184
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+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_75ceb321353780f53c0b+a9d440f5/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:17621d1c0828baa67b83082d43ae4fd71c5549e4b933e3543de0d35429366849
|
3 |
+
size 82265
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:242ebec44f8cf33e2c44ffbafd1451402c81cdc182bc6f20a4a176ad98a3af7d
|
3 |
+
size 246784
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_75ceb321353780f53c0b+a9d440f5/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba0343be401c64cb2827fe18b6324bca0d81ad99f8b09e3c491f9bf7e97ef7d3
|
3 |
+
size 254591
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+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_901275bef8665064964c+a9d440f5/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00c6665c365ab0da459979eae7bfa5988a54c62c5ef028861aba356060730803
|
3 |
+
size 81649
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b8b314a3f778679299f4635beae8dc5d1e98e1c03645cb4a0ffbdf873cdfcc44
|
3 |
+
size 246784
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_901275bef8665064964c+a9d440f5/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc38a0aedf3d54cf3f40cc6804246dcd6ecc6692a93226faabc0fbb1b238cc7f
|
3 |
+
size 254591
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+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_e23cd3c3922eefeb7287+ed72d204/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+ed72d204/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:309ecb7452fd67e7d5433e06b119fefb4ee796db045d68f2af040b4fd42bb2de
|
3 |
+
size 78947
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e23cd3c3922eefeb7287+ed72d204/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e9e2047821839bdeda4aee878b88d856461ac175c50572229ae33a9e29800298
|
3 |
+
size 513024
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+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_e9ae76ce87d9056639c1+ed72d204/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+ed72d204/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57b5b81c43e54e9946e228d28a61313aaa344d2e435c91369f39cfd724a935cc
|
3 |
+
size 74597
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e9ae76ce87d9056639c1+ed72d204/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c5538a174ad41242dcc309f0cffb05f962d86f14575c30387abbb1209e4fe43
|
3 |
+
size 308224
|