Synchronizing local compiler cache.

.gitattributes

@@ -2324,3 +2324,16 @@ neuronxcc-2.17.194.0+d312836f/MODULE_3623ca04e2134aeaae63+793f1a96/model.neff fi
 neuronxcc-2.17.194.0+d312836f/MODULE_c64dbf51d7751bc4d5a5+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_c9975b78b6ea5810a58d+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_c9975b78b6ea5810a58d+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_3957da6ebe3dd483b584+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_395c548dd9a6d3722142+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_395c548dd9a6d3722142+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_47b49c104312abacbb79+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_71e1efcb3071f7cb00b6+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_71e1efcb3071f7cb00b6+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_7679b52d5f03b0a3e52a+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_b6551578a2d26cf0e433+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_bce95ac1b2d4df9f5b48+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_cf2d32e118f389e77f17+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_cf2d32e118f389e77f17+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_de0cb04f05e1509e85d4+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_de0cb04f05e1509e85d4+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/e2fa63eb39084b138562.json

@@ -0,0 +1,77 @@
+{
+  "_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": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "continuous_batching": false,
+    "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": 1,
+    "max_context_length": 131072,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 131072,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.2.0.dev5",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 131072,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "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/MODULE_25cb3acfd7931dee158b+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_25cb3acfd7931dee158b+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82a4468f10d230f344133e3d413f1e6e21a9fc56f972c9a4ef54659b147d5a69
+size 7106

neuronxcc-2.17.194.0+d312836f/MODULE_3957da6ebe3dd483b584+793f1a96/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 ' -O1  --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_3957da6ebe3dd483b584+793f1a96/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a02e9ccc29e6da3480938961adc21cdd190bad8cd98fa2bcd5a16fc6e185395
+size 448531

neuronxcc-2.17.194.0+d312836f/MODULE_3957da6ebe3dd483b584+793f1a96/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00dee85928a1f9b7ae0871aedd0ebccb032c8700adbeaafe94d93f3a79ef680
+size 25181184

neuronxcc-2.17.194.0+d312836f/MODULE_395c548dd9a6d3722142+7e4da68b/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 ' -O1  --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_395c548dd9a6d3722142+7e4da68b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddd11f9c02b52d7f705aeb808f36b3f9f29a503ad5149d528b8a37c590182676
+size 413964

neuronxcc-2.17.194.0+d312836f/MODULE_395c548dd9a6d3722142+7e4da68b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed184f3f77a84fc4dff596704bc40263d775e8c199cfc8eb838654670074f5dc
+size 2212864

neuronxcc-2.17.194.0+d312836f/MODULE_395c548dd9a6d3722142+7e4da68b/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f7e8c7c4bcf9fbac51e9cb9f08b09a3bb1fe949993e0e221e2926a9b12c0d4f
+size 2282608

neuronxcc-2.17.194.0+d312836f/MODULE_47b49c104312abacbb79+793f1a96/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 ' -O1  --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_47b49c104312abacbb79+793f1a96/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e66ec249ad16c992cbf5a9fe134b429f5ffb31015ad95d48b06163013e87f288
+size 80815

neuronxcc-2.17.194.0+d312836f/MODULE_47b49c104312abacbb79+793f1a96/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57fa508135d4d59208e9c9ee82cbb303908e76ad18de2fa2b03fffc37dfc0f2
+size 236544

neuronxcc-2.17.194.0+d312836f/MODULE_57cf1c9c1db90790e8c9+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_57cf1c9c1db90790e8c9+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fbf03bdca8871117888a18257ec507a634b0f975a450294af733fa147b17504
+size 7106

neuronxcc-2.17.194.0+d312836f/MODULE_71e1efcb3071f7cb00b6+7e4da68b/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 ' -O1  --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_71e1efcb3071f7cb00b6+7e4da68b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2512847fc86a3f6dea3d6fe8bf73ebef7fe77c7d887f66401fd43b31e24441
+size 82299

neuronxcc-2.17.194.0+d312836f/MODULE_71e1efcb3071f7cb00b6+7e4da68b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48eeb80f42a8107b570efe66a70149b11a5ecb522045fcc92ebca3bda66c43b9
+size 236544

neuronxcc-2.17.194.0+d312836f/MODULE_71e1efcb3071f7cb00b6+7e4da68b/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61fdfca0c1f8eccc9945c8adc0ec7530d73cc6f9995884bbab1cc6d631593ac
+size 244319

neuronxcc-2.17.194.0+d312836f/MODULE_7679b52d5f03b0a3e52a+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_7679b52d5f03b0a3e52a+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580bf01a47f9cc1abe14e28d6b87924f1be5f6e3761a0139fc65cb48ad7404b5
+size 69051

neuronxcc-2.17.194.0+d312836f/MODULE_7679b52d5f03b0a3e52a+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14988dfdc69fd92e9d50ee823bd367f24f957b2ab6065b156d83992c506d792d
+size 1158144

neuronxcc-2.17.194.0+d312836f/MODULE_b6551578a2d26cf0e433+793f1a96/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 ' -O1  --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_b6551578a2d26cf0e433+793f1a96/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4df4ddcde0818d80562fddaaec000c6df317e66662ae25e172b1365c890cbd5
+size 80244

neuronxcc-2.17.194.0+d312836f/MODULE_b6551578a2d26cf0e433+793f1a96/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73efc545834d724084154bc14cc48f9ffced7673348a2f87cfafdd3c6ae08a73
+size 226304

neuronxcc-2.17.194.0+d312836f/MODULE_bce95ac1b2d4df9f5b48+793f1a96/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 ' -O1  --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_bce95ac1b2d4df9f5b48+793f1a96/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fc25da67cce0cd0213ee3dcc3c868aa3e36fdb4d63183e28b0f7a612d50aea1
+size 80244

neuronxcc-2.17.194.0+d312836f/MODULE_bce95ac1b2d4df9f5b48+793f1a96/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:114adae7470f048fa548c77a0570ddef2d92f6e2ce59e8a4a23a7b00cdae2676
+size 226304

neuronxcc-2.17.194.0+d312836f/MODULE_c671356c64ab8a366139+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_c671356c64ab8a366139+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b706b02fcf5d239ef2b5374d3aac8a84187b8463757f5c6bc13251fd24dacab
+size 7106

neuronxcc-2.17.194.0+d312836f/MODULE_cf2d32e118f389e77f17+7e4da68b/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 ' -O1  --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_cf2d32e118f389e77f17+7e4da68b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b82617b73b42642502743459932ea40e4eed2cf2ea7e758bc62f1aef72ee5c97
+size 82299

neuronxcc-2.17.194.0+d312836f/MODULE_cf2d32e118f389e77f17+7e4da68b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b82744b2ed277051ad8130521d3371efe39cc491bbd7adf43d8a26d6b6d8265
+size 236544

neuronxcc-2.17.194.0+d312836f/MODULE_cf2d32e118f389e77f17+7e4da68b/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcaccebd91e984f1c1cb795e8c454f6d9d9b03264e78538f99fc915a62b0a02c
+size 244319

neuronxcc-2.17.194.0+d312836f/MODULE_de0cb04f05e1509e85d4+7e4da68b/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 ' -O1  --internal-num-neuroncores-per-sengine=1 --logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt --enable-internal-neff-wrapper"