Synchronizing local compiler cache.

.gitattributes

@@ -12212,3 +12212,6 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_9aa5b581f9d17855f430+c2248236/model.neff
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_62245507fa1f848be542+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_a104e1d968fe30c4ac21+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_a104e1d968fe30c4ac21+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_050801613474e5a8dafe+c2248236/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.1.dev0/mixtral/mistralai/Mixtral-8x22B-Instruct-v0.1/2de1699eb875f950d938.json

@@ -0,0 +1,58 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "mistralai/Mixtral-8x22B-Instruct-v0.1",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 16384,
+  "max_position_embeddings": 65536,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "mistralai/Mixtral-8x22B-Instruct-v0.1",
+    "checkpoint_revision": "cc88a6cc19fbd17d9f1c0ee0b0d70a748dce698d",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 64,
+    "max_batch_size": 1,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.4.1.dev0",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn1",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 64
+  },
+  "num_attention_heads": 48,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 56,
+  "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": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32768
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_050801613474e5a8dafe+c2248236/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/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_050801613474e5a8dafe+c2248236/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e755d518cc2d02cea1efff78ba96ca66fb8685df09c693296e3a4e8a18f1bed
+size 2438683

neuronxcc-2.21.18209.0+043b1bf7/MODULE_050801613474e5a8dafe+c2248236/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daaf3f55115d7fd8ad3fa9154799468dbd832d320252dba2ed61353dd34af8d6
+size 4291584

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4bf5da7e011d03e4233a+0b01cb42/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4bf5da7e011d03e4233a+0b01cb42/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89b72782a8cde38374080b8cf02fd825d65d6089d84e0fec990ffcec324e4ada
+size 1066523

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4bf5da7e011d03e4233a+0b01cb42/model.log

@@ -0,0 +1,2 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_4bf5da7e011d03e4233a+0b01cb42.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_4bf5da7e011d03e4233a+0b01cb42.neff', '--target=trn2', '--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_model/_tp0_bk0/log-neuron-cc.txt', '--enable-internal-neff-wrapper', '--verbose=35']: 2025-10-21T15:12:48Z 2025-10-21 15:12:48.519681: F hilo/hlo_passes/NeuronHloVerifier.cc:504] [ERROR] [NCC_VRF009] Memory requirement exceeds target architecture's HBM limit. Needed 23487730696 bytes (21 GB) vs. available 17179869184 bytes (16 GB). TIP: Consider using smaller batches or applying model parallelism
+

neuronxcc-2.21.18209.0+043b1bf7/MODULE_5907b22fb1f79eb2562e+0b01cb42/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_5907b22fb1f79eb2562e+0b01cb42/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce4aa5c537de792273197588f9c934f01f4b0a0c32a37bb94afea255d393efc
+size 1297455

neuronxcc-2.21.18209.0+043b1bf7/MODULE_5907b22fb1f79eb2562e+0b01cb42/model.log

@@ -0,0 +1,2 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_5907b22fb1f79eb2562e+0b01cb42.hlo_module.pb', '--output', '/tmp/nxd_model/token_generation_model/_tp0_bk0/model.MODULE_5907b22fb1f79eb2562e+0b01cb42.neff', '--target=trn2', '--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_model/_tp0_bk0/log-neuron-cc.txt', '--enable-internal-neff-wrapper', '--verbose=35']: 2025-10-21T15:14:19Z 2025-10-21 15:14:19.119164: F hilo/hlo_passes/NeuronHloVerifier.cc:504] [ERROR] [NCC_VRF009] Memory requirement exceeds target architecture's HBM limit. Needed 23890817056 bytes (22 GB) vs. available 17179869184 bytes (16 GB). TIP: Consider using smaller batches or applying model parallelism
+

neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/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_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cff9bbd09783c80111230c07d2efac680aaae1a2c61f3ee64f62b8bb097d6ec0
+size 1667462

neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75629a6c85a27eca61f437f4d95cfeb6dd6ddbab26f922e36430dbe21baf3c5f
+size 3124224

neuronxcc-2.21.18209.0+043b1bf7/MODULE_887a24107396c649d6c0+ca355898/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf05e6e5862148d804bd68009cc957580a8f28e4247af49d5ddd7f48dd2c4f8c
+size 3451260