Synchronizing local compiler cache.

.gitattributes

@@ -2888,3 +2888,7 @@ neuronxcc-2.18.121.0+9e31e41a/MODULE_ec432bd70b0f3bb72798+84f3e719/model.neff fi
 neuronxcc-2.18.121.0+9e31e41a/MODULE_f269665cd140e0a337fe+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_ff48ee0ab9cd762b3c1f+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.18.121.0+9e31e41a/MODULE_ff48ee0ab9cd762b3c1f+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_3d7f88b0a10f3671efc8+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_3d7f88b0a10f3671efc8+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_410ab2339c0623a8ea99+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_b02d75de24d831d530b4+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/llama/llamafactory/tiny-random-Llama-3/439224868ff2d187153d.json

@@ -0,0 +1,55 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "BSH",
+    "attn_output_transposed": false,
+    "auto_cast_type": "bf16",
+    "batch_size": 1,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": true,
+    "group_query_attention": null,
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.3.0.dev0",
+    "output_all_logits": false,
+    "sequence_length": 131072,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/2b10d94944cdae0f19a8.json

@@ -0,0 +1,71 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 4,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.3.0.dev0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "float16",
+    "sequence_length": 4096,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "float16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.17.194.0+d312836f/MODULE_3d7f88b0a10f3671efc8+165e9558/compile_flags.json

@@ -0,0 +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_3d7f88b0a10f3671efc8+165e9558/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd4bcf2094c905f1d9198a2fa36e2a067f7ae8fbf9c63e63b52365a14b5106e
+size 628200

neuronxcc-2.17.194.0+d312836f/MODULE_3d7f88b0a10f3671efc8+165e9558/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6444b8e73d32d5bf587c6fa0e6caafc5ba0d245ace20208adc0de261b1115b78
+size 3748864

neuronxcc-2.17.194.0+d312836f/MODULE_3d7f88b0a10f3671efc8+165e9558/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d878f479413f8ba944184c42b178ab5bf47641c26bd93e7880210602e8e4f34
+size 3862538

neuronxcc-2.17.194.0+d312836f/MODULE_410ab2339c0623a8ea99+bfe5714b/compile_flags.json

@@ -0,0 +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_410ab2339c0623a8ea99+bfe5714b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a1023e1695522602409828ff9af4d776589ed5f150f52e01493955f204b04c
+size 739176

neuronxcc-2.17.194.0+d312836f/MODULE_410ab2339c0623a8ea99+bfe5714b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8145f5f50c3569815d235cdab7fa87ca9e1efcf3bceec379141c6a8d90d57d5e
+size 19928064

neuronxcc-2.17.194.0+d312836f/MODULE_b02d75de24d831d530b4+431f5505/compile_flags.json

@@ -0,0 +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_b02d75de24d831d530b4+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4e5d9a94b12f00a88c9fe5a8361dbf26f5641f9ad46ffdee5d5243ed31b78e
+size 113548

neuronxcc-2.17.194.0+d312836f/MODULE_b02d75de24d831d530b4+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f11216420014d8ea987810401d8d317f4d6699532b3d7b77d75081e1849463
+size 564224