Synchronizing local compiler cache.
Browse files- .gitattributes +3 -0
- neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/37f7f1639bd7680a860b.json +64 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_238f936f6792c3472f34+24129607/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/compile_flags.json +1 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/model.done +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/model.hlo_module.pb +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/model.neff +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_78c9e4beae8ae2b514a7+24129607/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_9fe6e286c1c48b3cf2a9+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_9fe6e286c1c48b3cf2a9+a02c3a36/wrapped_neff.hlo +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_a6d912262b31e81edfe6+24129607/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/compile_flags.json +1 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/model.done +0 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/model.hlo_module.pb +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/model.neff +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/wrapped_neff.hlo +3 -0
- neuronxcc-2.21.33363.0+82129205/MODULE_f6a3ff2ad752e338116c+a02c3a36/model.neff +1 -1
- neuronxcc-2.21.33363.0+82129205/MODULE_f6a3ff2ad752e338116c+a02c3a36/wrapped_neff.hlo +1 -1
.gitattributes
CHANGED
|
@@ -5944,3 +5944,6 @@ neuronxcc-2.22.12471.0+b4a00d10/MODULE_55fa69e3aa0c7efc18a4+519f203d/model.neff
|
|
| 5944 |
neuronxcc-2.21.33363.0+82129205/MODULE_39061f1efbca2332dc73+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5945 |
neuronxcc-2.21.33363.0+82129205/MODULE_1aa5f4baa9354745d6a6+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5946 |
neuronxcc-2.21.33363.0+82129205/MODULE_88399bbf2a34b1e28eee+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
| 5944 |
neuronxcc-2.21.33363.0+82129205/MODULE_39061f1efbca2332dc73+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5945 |
neuronxcc-2.21.33363.0+82129205/MODULE_1aa5f4baa9354745d6a6+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5946 |
neuronxcc-2.21.33363.0+82129205/MODULE_88399bbf2a34b1e28eee+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5947 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5948 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/model.neff filter=lfs diff=lfs merge=lfs -text
|
| 5949 |
+
neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
|
neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.4.dev2/llama/unsloth/Llama-3.2-1B-Instruct/37f7f1639bd7680a860b.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_entry_class": "SingleModelCacheEntry",
|
| 3 |
+
"_model_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 4 |
+
"_task": "text-generation",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LlamaForCausalLM"
|
| 7 |
+
],
|
| 8 |
+
"attention_bias": false,
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"dtype": "bfloat16",
|
| 11 |
+
"head_dim": 64,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 2048,
|
| 14 |
+
"initializer_range": 0.02,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"max_position_embeddings": 131072,
|
| 17 |
+
"mlp_bias": false,
|
| 18 |
+
"model_type": "llama",
|
| 19 |
+
"neuron": {
|
| 20 |
+
"_serialized_key": "NxDNeuronConfig",
|
| 21 |
+
"batch_size": 1,
|
| 22 |
+
"capacity_factor": null,
|
| 23 |
+
"checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
|
| 24 |
+
"checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
|
| 25 |
+
"continuous_batching": false,
|
| 26 |
+
"ep_degree": 1,
|
| 27 |
+
"fused_qkv": true,
|
| 28 |
+
"glu_mlp": true,
|
| 29 |
+
"local_ranks_size": 2,
|
| 30 |
+
"max_batch_size": 1,
|
| 31 |
+
"max_context_length": 4096,
|
| 32 |
+
"max_topk": 256,
|
| 33 |
+
"n_active_tokens": 4096,
|
| 34 |
+
"neuronxcc_version": "2.21.33363.0+82129205",
|
| 35 |
+
"on_device_sampling": true,
|
| 36 |
+
"optimum_neuron_version": "0.4.4.dev2",
|
| 37 |
+
"output_logits": false,
|
| 38 |
+
"pp_degree": 1,
|
| 39 |
+
"sequence_length": 4096,
|
| 40 |
+
"sequence_parallel_enabled": false,
|
| 41 |
+
"speculation_length": 0,
|
| 42 |
+
"start_rank_id": 0,
|
| 43 |
+
"target": "trn1",
|
| 44 |
+
"torch_dtype": "bfloat16",
|
| 45 |
+
"tp_degree": 2
|
| 46 |
+
},
|
| 47 |
+
"num_attention_heads": 32,
|
| 48 |
+
"num_hidden_layers": 16,
|
| 49 |
+
"num_key_value_heads": 8,
|
| 50 |
+
"pretraining_tp": 1,
|
| 51 |
+
"rms_norm_eps": 1e-05,
|
| 52 |
+
"rope_scaling": {
|
| 53 |
+
"factor": 32.0,
|
| 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": true,
|
| 61 |
+
"unsloth_fixed": true,
|
| 62 |
+
"use_cache": true,
|
| 63 |
+
"vocab_size": 128256
|
| 64 |
+
}
|
neuronxcc-2.21.33363.0+82129205/MODULE_238f936f6792c3472f34+24129607/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14644224
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3bc84c662b5fab8d927c1faeeb0dca751fd1f4048e013936a22011c85e8d154
|
| 3 |
size 14644224
|
neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/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/_tp0_bk0/log-neuron-cc.txt"]
|
neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fa60c9ce8de33b02366450a36e239b7a83bb2caef842b87525f856a0c51576c
|
| 3 |
+
size 471625
|
neuronxcc-2.21.33363.0+82129205/MODULE_2fcf7c990c6fe04fecca+24129607/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74458bb058b81899ca02684781170f7b61422576d137cdb2a2c9b0216d751bc2
|
| 3 |
+
size 114893824
|
neuronxcc-2.21.33363.0+82129205/MODULE_78c9e4beae8ae2b514a7+24129607/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5223424
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d06f75a1e4b52e3c6677ce2384b543882d8ea3cdb9cd281c78f12844ed9d25e5
|
| 3 |
size 5223424
|
neuronxcc-2.21.33363.0+82129205/MODULE_9fe6e286c1c48b3cf2a9+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12411904
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:67a2afa1e975e6f17aff377c0d882e1d5607d1648ec03a9559820318b24b7de9
|
| 3 |
size 12411904
|
neuronxcc-2.21.33363.0+82129205/MODULE_9fe6e286c1c48b3cf2a9+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 12558920
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dc8f9adfa9882a7212d3390f7feae5392fafc4121eaf1036b1e37b796bd56e6
|
| 3 |
size 12558920
|
neuronxcc-2.21.33363.0+82129205/MODULE_a6d912262b31e81edfe6+24129607/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 114013184
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fcd0208f93d0034e8ba27de29cacfb822d98c06bc860349612fef53ad374a7
|
| 3 |
size 114013184
|
neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/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/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]
|
neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/model.done
ADDED
|
File without changes
|
neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/model.hlo_module.pb
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:df2bfc224ba5b7eb401944f176848782435de31560cbc75c768739d851f495f4
|
| 3 |
+
size 398951
|
neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/model.neff
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0bdaa2b3178472459a72d3432576eb34d265af9fda821e9a074f9646df85ebdb
|
| 3 |
+
size 2315264
|
neuronxcc-2.21.33363.0+82129205/MODULE_c5df6a2849dc2a262550+a02c3a36/wrapped_neff.hlo
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d31a08e6e5048da612ee398da3da4d3607bca3b7b1f270e968d0290ffbc2b30
|
| 3 |
+
size 2389212
|
neuronxcc-2.21.33363.0+82129205/MODULE_f6a3ff2ad752e338116c+a02c3a36/model.neff
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5008384
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9313704e927115bf13417b3e5a9ec30f8110a95faafa6e618a62a5a8bb57b41c
|
| 3 |
size 5008384
|
neuronxcc-2.21.33363.0+82129205/MODULE_f6a3ff2ad752e338116c+a02c3a36/wrapped_neff.hlo
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5192563
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:751851802621b827355ab22caefb2171bebad4082053c0f31138e142b0491811
|
| 3 |
size 5192563
|