Synchronizing local compiler cache.

.gitattributes

@@ -16869,3 +16869,5 @@ neuronxcc-2.21.33363.0+82129205/MODULE_9fea03a5ffd4ddf2503c+a02c3a36/model.neff
 neuronxcc-2.21.33363.0+82129205/MODULE_9fea03a5ffd4ddf2503c+a02c3a36/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_0100b6d92f868602c5a7+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.33363.0+82129205/MODULE_0100b6d92f868602c5a7+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_188a76996323b799a32c+80d05c3f/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.33363.0+82129205/MODULE_188a76996323b799a32c+80d05c3f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/2aae7cc49f53a364c1bfabafaecff51826622f8f3ade9b884d1f5aa9b6107830/5c8465e879fd61103f2d.json

@@ -0,0 +1,58 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "checkpoint_revision": "eba92302a2861cdc0098cc54bc9f17cb2c47eb61",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 32,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.6.dev2",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 32
+  },
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32000
+}

neuronxcc-2.21.33363.0+82129205/0_REGISTRY/0.4.6.dev2/mixtral/mistralai/Mixtral-8x7B-Instruct-v0.1/5c8465e879fd61103f2d.json

@@ -0,0 +1,58 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "checkpoint_revision": "eba92302a2861cdc0098cc54bc9f17cb2c47eb61",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 32,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.33363.0+82129205",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.6.dev2",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 32
+  },
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32000
+}

neuronxcc-2.21.33363.0+82129205/MODULE_188a76996323b799a32c+80d05c3f/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--enable-saturate-infinity", "--enable-mixed-precision-accumulation", "--model-type", "transformer", "-O1", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2", "--auto-cast=none", "--internal-enable-dge-levels", "vector_dynamic_offsets", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.33363.0+82129205/MODULE_188a76996323b799a32c+80d05c3f/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d58a17d995151fc262ccfeb6b3fc288a8100af820c263775c897c701574c249f
+size 964829

neuronxcc-2.21.33363.0+82129205/MODULE_188a76996323b799a32c+80d05c3f/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddae101057ad489ee1b0b2081658947d2bf690b5469e222d05a67bf736a9482b
+size 2171904

neuronxcc-2.21.33363.0+82129205/MODULE_188a76996323b799a32c+80d05c3f/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99cb320935b9818f30ab28ef0c056faf1b302dd5eff1f3d606e543cb2fafb4fd
+size 2342632