Synchronizing local compiler cache.
Browse files- .gitattributes +7 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/gpt_oss/tengomucho/tiny-random-gpt-oss/06d97ec0faf0c1167dd0.json +79 -0
- neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/gpt_oss/tengomucho/tiny-random-gpt-oss/c7d322ad06b1d0f920a0.json +79 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+ed72d204/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+ed72d204/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+ed72d204/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+ed72d204/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+431f5505/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+431f5505/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+431f5505/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+431f5505/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/wrapped_neff.hlo +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d72bf8688528b216493a+431f5505/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d72bf8688528b216493a+431f5505/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d72bf8688528b216493a+431f5505/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_d72bf8688528b216493a+431f5505/model.neff +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/compile_flags.json +1 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/model.done +0 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/model.hlo_module.pb +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/model.neff +3 -0
- neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/wrapped_neff.hlo +3 -0
.gitattributes
CHANGED
@@ -3730,3 +3730,10 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_d08ea0c04146228470b3+ed72d204/model.neff f
|
|
3730 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f2c41900e04be039a7f8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
3731 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f968d6b60e2b3b9e4cd1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
3732 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f968d6b60e2b3b9e4cd1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3730 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f2c41900e04be039a7f8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
3731 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f968d6b60e2b3b9e4cd1+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
3732 |
neuronxcc-2.19.8089.0+8ab9f450/MODULE_f968d6b60e2b3b9e4cd1+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
3733 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
3734 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
|
3735 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
|
3736 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
3737 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
3738 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
|
3739 |
+
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/gpt_oss/tengomucho/tiny-random-gpt-oss/06d97ec0faf0c1167dd0.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "tengomucho/tiny-random-gpt-oss",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"GptOssForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_bias": true,
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 384,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 512,
|
15 |
+
"layer_types": [
|
16 |
+
"sliding_attention",
|
17 |
+
"full_attention"
|
18 |
+
],
|
19 |
+
"max_position_embeddings": 8192,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "gpt_oss",
|
22 |
+
"neuron": {
|
23 |
+
"_serialized_key": "NxDNeuronConfig",
|
24 |
+
"async_mode": false,
|
25 |
+
"attn_kernel_enabled": false,
|
26 |
+
"batch_size": 1,
|
27 |
+
"capacity_factor": null,
|
28 |
+
"cc_pipeline_tiling_factor": 2,
|
29 |
+
"checkpoint_id": "tengomucho/tiny-random-gpt-oss",
|
30 |
+
"checkpoint_revision": "2109d1ee033bb4191af6dd950fda542c9c351dc8",
|
31 |
+
"continuous_batching": false,
|
32 |
+
"enable_bucketing": false,
|
33 |
+
"ep_degree": 1,
|
34 |
+
"flash_decoding_enabled": false,
|
35 |
+
"fused_qkv": false,
|
36 |
+
"glu_mlp": true,
|
37 |
+
"is_chunked_prefill": false,
|
38 |
+
"local_ranks_size": 2,
|
39 |
+
"logical_nc_config": 1,
|
40 |
+
"max_batch_size": 1,
|
41 |
+
"max_context_length": 4096,
|
42 |
+
"max_topk": 256,
|
43 |
+
"mlp_kernel_enabled": false,
|
44 |
+
"mlp_kernel_fuse_residual_add": false,
|
45 |
+
"n_active_tokens": 4096,
|
46 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
47 |
+
"num_cores_per_group": 1,
|
48 |
+
"on_device_sampling": false,
|
49 |
+
"optimum_neuron_version": "0.3.0.dev5",
|
50 |
+
"output_logits": false,
|
51 |
+
"padding_side": "right",
|
52 |
+
"pp_degree": 1,
|
53 |
+
"qk_layernorm": false,
|
54 |
+
"qkv_kernel_enabled": false,
|
55 |
+
"rpl_reduce_dtype": "bfloat16",
|
56 |
+
"sequence_length": 4096,
|
57 |
+
"sequence_parallel_enabled": false,
|
58 |
+
"speculation_length": 0,
|
59 |
+
"start_rank_id": 0,
|
60 |
+
"target": null,
|
61 |
+
"torch_dtype": "bfloat16",
|
62 |
+
"tp_degree": 2,
|
63 |
+
"vocab_parallel": false
|
64 |
+
},
|
65 |
+
"num_attention_heads": 18,
|
66 |
+
"num_experts_per_tok": 4,
|
67 |
+
"num_hidden_layers": 2,
|
68 |
+
"num_key_value_heads": 2,
|
69 |
+
"num_local_experts": 64,
|
70 |
+
"output_router_logits": false,
|
71 |
+
"rms_norm_eps": 1e-05,
|
72 |
+
"rope_scaling": null,
|
73 |
+
"rope_theta": 150000.0,
|
74 |
+
"router_aux_loss_coef": 0.9,
|
75 |
+
"sliding_window": 128,
|
76 |
+
"tie_word_embeddings": false,
|
77 |
+
"use_cache": true,
|
78 |
+
"vocab_size": 201088
|
79 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/gpt_oss/tengomucho/tiny-random-gpt-oss/c7d322ad06b1d0f920a0.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_entry_class": "SingleModelCacheEntry",
|
3 |
+
"_model_id": "tengomucho/tiny-random-gpt-oss",
|
4 |
+
"_task": "text-generation",
|
5 |
+
"architectures": [
|
6 |
+
"GptOssForCausalLM"
|
7 |
+
],
|
8 |
+
"attention_bias": true,
|
9 |
+
"attention_dropout": 0.0,
|
10 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 384,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 512,
|
15 |
+
"layer_types": [
|
16 |
+
"sliding_attention",
|
17 |
+
"full_attention"
|
18 |
+
],
|
19 |
+
"max_position_embeddings": 8192,
|
20 |
+
"mlp_bias": false,
|
21 |
+
"model_type": "gpt_oss",
|
22 |
+
"neuron": {
|
23 |
+
"_serialized_key": "NxDNeuronConfig",
|
24 |
+
"async_mode": false,
|
25 |
+
"attn_kernel_enabled": false,
|
26 |
+
"batch_size": 1,
|
27 |
+
"capacity_factor": null,
|
28 |
+
"cc_pipeline_tiling_factor": 2,
|
29 |
+
"checkpoint_id": "tengomucho/tiny-random-gpt-oss",
|
30 |
+
"checkpoint_revision": "4789d7f7c58b72525aefd1ae204ccb9ad450df49",
|
31 |
+
"continuous_batching": false,
|
32 |
+
"enable_bucketing": false,
|
33 |
+
"ep_degree": 1,
|
34 |
+
"flash_decoding_enabled": false,
|
35 |
+
"fused_qkv": false,
|
36 |
+
"glu_mlp": true,
|
37 |
+
"is_chunked_prefill": false,
|
38 |
+
"local_ranks_size": 2,
|
39 |
+
"logical_nc_config": 1,
|
40 |
+
"max_batch_size": 1,
|
41 |
+
"max_context_length": 4096,
|
42 |
+
"max_topk": 256,
|
43 |
+
"mlp_kernel_enabled": false,
|
44 |
+
"mlp_kernel_fuse_residual_add": false,
|
45 |
+
"n_active_tokens": 4096,
|
46 |
+
"neuronxcc_version": "2.19.8089.0+8ab9f450",
|
47 |
+
"num_cores_per_group": 1,
|
48 |
+
"on_device_sampling": false,
|
49 |
+
"optimum_neuron_version": "0.3.0.dev5",
|
50 |
+
"output_logits": false,
|
51 |
+
"padding_side": "right",
|
52 |
+
"pp_degree": 1,
|
53 |
+
"qk_layernorm": false,
|
54 |
+
"qkv_kernel_enabled": false,
|
55 |
+
"rpl_reduce_dtype": "bfloat16",
|
56 |
+
"sequence_length": 4096,
|
57 |
+
"sequence_parallel_enabled": false,
|
58 |
+
"speculation_length": 0,
|
59 |
+
"start_rank_id": 0,
|
60 |
+
"target": null,
|
61 |
+
"torch_dtype": "bfloat16",
|
62 |
+
"tp_degree": 2,
|
63 |
+
"vocab_parallel": false
|
64 |
+
},
|
65 |
+
"num_attention_heads": 18,
|
66 |
+
"num_experts_per_tok": 4,
|
67 |
+
"num_hidden_layers": 2,
|
68 |
+
"num_key_value_heads": 2,
|
69 |
+
"num_local_experts": 64,
|
70 |
+
"output_router_logits": false,
|
71 |
+
"rms_norm_eps": 1e-05,
|
72 |
+
"rope_scaling": null,
|
73 |
+
"rope_theta": 150000.0,
|
74 |
+
"router_aux_loss_coef": 0.9,
|
75 |
+
"sliding_window": 128,
|
76 |
+
"tie_word_embeddings": false,
|
77 |
+
"use_cache": true,
|
78 |
+
"vocab_size": 201088
|
79 |
+
}
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+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_23cd48d5fa200c406e5b+ed72d204/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+ed72d204/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46b4e16557c45acae458da9a47933953ac92e2a4ab34ef78051a50514eed8783
|
3 |
+
size 42436031
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_23cd48d5fa200c406e5b+ed72d204/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eaa04e3a59fbb6f9e5d5b65b222ea3f2046a9a83328033cd9925c053c0ca0896
|
3 |
+
size 34847744
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+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_89f81fed0f7ac4ac31a8+ed72d204/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+ed72d204/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8936f20be694e01fad6e9ec5f4e43722d2eadef94fc4d71acc21892a7c3b695c
|
3 |
+
size 19441403
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_89f81fed0f7ac4ac31a8+ed72d204/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3815acd0ca6de7a7bc6f9967bbe96e783d8917f0f85f6b4334934ce1655738e8
|
3 |
+
size 4844544
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+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_a010d5b56ae0bd72ba99+431f5505/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+431f5505/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97ae43b05c925b01471e9387631507ae007b653990c68439ea3b01394cedfeaa
|
3 |
+
size 27900
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_a010d5b56ae0bd72ba99+431f5505/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f98fe3f137d1a5b41c20206623c889f7a83022347ffb75145ff6a1e8544a2f8
|
3 |
+
size 216064
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+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_ba2c4b7abceeb84f9017+a9d440f5/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cee635468faec550c528131ef1d3ac0a354816a913a80f01337b0d7561e4c817
|
3 |
+
size 84903
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7705efb721713c9b4ba8c47f42db87905ceba0893f45143fe82f73ba6938ec60
|
3 |
+
size 369664
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_ba2c4b7abceeb84f9017+a9d440f5/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e732502d3344b8adca044b3cca38a2415ca90ec8ce2c142a2d85bfe58a84f610
|
3 |
+
size 383598
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d72bf8688528b216493a+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_d72bf8688528b216493a+431f5505/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d72bf8688528b216493a+431f5505/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebbf62364a38673cbe6ec1bdbef089250ad1aa4e0a64e1331d0cea754ca9ca37
|
3 |
+
size 14119
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_d72bf8688528b216493a+431f5505/model.neff
ADDED
Binary file (62.5 kB). View file
|
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+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_e389728de68772abbfd8+a9d440f5/model.done
ADDED
File without changes
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/model.hlo_module.pb
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0dd7664de3c249191dc8192dc5f887b692057b0b3c43262b5aad82b289ad0160
|
3 |
+
size 163859
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/model.neff
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:779192227798181998face3d7536bc6006ba6c260a70fbf6b09671ef89f805d5
|
3 |
+
size 748544
|
neuronxcc-2.19.8089.0+8ab9f450/MODULE_e389728de68772abbfd8+a9d440f5/wrapped_neff.hlo
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d2ee89a6d2a39d634448845fe39e0104626fa39d534a702ac6515c724021319
|
3 |
+
size 775632
|