Synchronizing local compiler cache.

.gitattributes

@@ -13312,3 +13312,21 @@ neuronxcc-2.21.18209.0+043b1bf7/MODULE_e6150818c39bca2677d1+8eeafb64/model.neff
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_e6150818c39bca2677d1+8eeafb64/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_f2f5d7eea0d7ac74facb+26bb721a/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.21.18209.0+043b1bf7/MODULE_f2f5d7eea0d7ac74facb+26bb721a/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_05be74483bc93c8757df+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_05be74483bc93c8757df+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_30b7f3226f615e011f33+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_3b867487803e851b46f0+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_3b867487803e851b46f0+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_416e0fa403c0921df6c3+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4200960674e1921e9aec+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_4ec3b67fd9a78f7cbdb4+a32116a7/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_65e34d6afbea63ef1564+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_65e34d6afbea63ef1564+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_a42f0ea98535622da192+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_a42f0ea98535622da192+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_b50fd34438465c143456+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_b50fd34438465c143456+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec5bfc4ef4ea5c5e3798+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_ec5bfc4ef4ea5c5e3798+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_f850227f2a268ed6719b+ac10809c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.21.18209.0+043b1bf7/MODULE_f850227f2a268ed6719b+ac10809c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.3.dev1/llama4_text/meta-llama/Llama-4-Maverick-17B-128E-Instruct/0782cbf4b3ed6eea7218.json

@@ -0,0 +1,190 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
+  "_task": "text-generation",
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": true,
+  "dtype": "bfloat16",
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 2,
+  "intermediate_size": 8192,
+  "intermediate_size_mlp": 16384,
+  "layer_types": [
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 1048576,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    1,
+    3,
+    5,
+    7,
+    9,
+    11,
+    13,
+    15,
+    17,
+    19,
+    21,
+    23,
+    25,
+    27,
+    29,
+    31,
+    33,
+    35,
+    37,
+    39,
+    41,
+    43,
+    45,
+    47
+  ],
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
+    "checkpoint_revision": "73d14711bcc77c16df3470856949c3764056b617",
+    "continuous_batching": 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": true,
+    "optimum_neuron_version": "0.4.3.dev1",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 64
+  },
+  "no_rope_layers": [
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0
+  ],
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 202048
+}

neuronxcc-2.21.18209.0+043b1bf7/0_REGISTRY/0.4.3.dev1/llama4_text/meta-llama/Llama-4-Maverick-17B-128E-Instruct/9fc13314975962cba5a6.json

@@ -0,0 +1,190 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
+  "_task": "text-generation",
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": true,
+  "dtype": "bfloat16",
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 2,
+  "intermediate_size": 8192,
+  "intermediate_size_mlp": 16384,
+  "layer_types": [
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 1048576,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    1,
+    3,
+    5,
+    7,
+    9,
+    11,
+    13,
+    15,
+    17,
+    19,
+    21,
+    23,
+    25,
+    27,
+    29,
+    31,
+    33,
+    35,
+    37,
+    39,
+    41,
+    43,
+    45,
+    47
+  ],
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct",
+    "checkpoint_revision": "73d14711bcc77c16df3470856949c3764056b617",
+    "continuous_batching": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 64,
+    "max_batch_size": 1,
+    "max_context_length": 8192,
+    "max_topk": 256,
+    "n_active_tokens": 8192,
+    "neuronxcc_version": "2.21.18209.0+043b1bf7",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.4.3.dev1",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 8192,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": "trn2",
+    "torch_dtype": "bfloat16",
+    "tp_degree": 64
+  },
+  "no_rope_layers": [
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0,
+    1,
+    1,
+    1,
+    0
+  ],
+  "num_attention_heads": 40,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "num_local_experts": 128,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_qk_norm": false,
+  "vocab_size": 202048
+}

neuronxcc-2.21.18209.0+043b1bf7/MODULE_05be74483bc93c8757df+ac10809c/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_05be74483bc93c8757df+ac10809c/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024adf15e89a8497d981f4e938a3324f26464df0317c371a54b04a9af78bbbab
+size 203660169

neuronxcc-2.21.18209.0+043b1bf7/MODULE_05be74483bc93c8757df+ac10809c/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308e47f230df190897ed9e5282bf56ec98ed13a3d7a92ec4b1b666d845d1d289
+size 11254784

neuronxcc-2.21.18209.0+043b1bf7/MODULE_05be74483bc93c8757df+ac10809c/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a81d483014f7a46d5e5ef1038c202899a516f7925b20a4b24698c050fe1e0ff
+size 11564149

neuronxcc-2.21.18209.0+043b1bf7/MODULE_30b7f3226f615e011f33+a32116a7/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_30b7f3226f615e011f33+a32116a7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcaea021293d4d4472d7afda78070bec3b2760e9f748cd882859201d1a26917b
+size 107351189

neuronxcc-2.21.18209.0+043b1bf7/MODULE_30b7f3226f615e011f33+a32116a7/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c059eda8abaeb544f662db22082ce4b294a6af28bc592db36e86c4a8ca6ebad5
+size 39937024

neuronxcc-2.21.18209.0+043b1bf7/MODULE_3b867487803e851b46f0+ac10809c/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_3b867487803e851b46f0+ac10809c/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d996d1b6b51ba153eff193f4ee2995efe72f50f85f41dc33347c7a3f3b57fe4
+size 204269521

neuronxcc-2.21.18209.0+043b1bf7/MODULE_3b867487803e851b46f0+ac10809c/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba38c5f2f4aa3906bfab6e329ad29bc4eef48551c1b39f710c70cb42d9709c58
+size 11316224

neuronxcc-2.21.18209.0+043b1bf7/MODULE_3b867487803e851b46f0+ac10809c/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ce2961eab1a7f057e1d2a01fa3066a66c28ed8b5478a78b7c0f867f1ac69af
+size 11625573

neuronxcc-2.21.18209.0+043b1bf7/MODULE_416e0fa403c0921df6c3+a32116a7/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_416e0fa403c0921df6c3+a32116a7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e540c4f1e31e36c9b251c7099e31307fc0d1e6008b967542cd4239534e1c9feb
+size 208063973

neuronxcc-2.21.18209.0+043b1bf7/MODULE_416e0fa403c0921df6c3+a32116a7/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4082b934fd93cfc3969a5b641b273afaa8002499e848790bad7912a07a4ad01
+size 77569024

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4200960674e1921e9aec+a32116a7/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4200960674e1921e9aec+a32116a7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f6f942527d5e73f3ee38027454e1c6f85c9b3073d9acb209127e2b68f7e7ead
+size 208356581

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4200960674e1921e9aec+a32116a7/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7bd52b12ed63676b9008ab140fee0705f1afefa7b2be860962fcf9902f84e5d
+size 77579264

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4ec3b67fd9a78f7cbdb4+a32116a7/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4ec3b67fd9a78f7cbdb4+a32116a7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f287de9e03fb9e81b450ba63b209b2cedc3906bbdb3de4ab291532276186ec
+size 207847637

neuronxcc-2.21.18209.0+043b1bf7/MODULE_4ec3b67fd9a78f7cbdb4+a32116a7/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e43e6fe7e06e1f1bc0a66df6b299ded92c4a335a23d3c984a6a8544da3b080e
+size 77569024

neuronxcc-2.21.18209.0+043b1bf7/MODULE_65e34d6afbea63ef1564+ac10809c/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_65e34d6afbea63ef1564+ac10809c/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:833c44de5240e3c4e4dc6986a3d3429c0b1e6ed7a75c4b505c28216f9d85a76c
+size 204263377

neuronxcc-2.21.18209.0+043b1bf7/MODULE_65e34d6afbea63ef1564+ac10809c/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0bc0ef0a08a71504b94db3e2733a14e9307a354b66e5b499ee2118db26807de
+size 11070464

neuronxcc-2.21.18209.0+043b1bf7/MODULE_65e34d6afbea63ef1564+ac10809c/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9a303d035b0d4a4a595ee9dfc6211e558bf2943c767ee3af6a4d46f2b55292
+size 11379813

neuronxcc-2.21.18209.0+043b1bf7/MODULE_674332a679782ee04898+a32116a7/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_674332a679782ee04898+a32116a7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dce21659a8523d02dcd06c067d00863c54f39f5e180742c35e54fedb64d5680
+size 233570789

neuronxcc-2.21.18209.0+043b1bf7/MODULE_674332a679782ee04898+a32116a7/model.log

@@ -0,0 +1,3 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_674332a679782ee04898+a32116a7.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_674332a679782ee04898+a32116a7.neff', '--target=trn2', '--auto-cast=none', '--model-type=transformer', '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ', '-O2', '--lnc=2', '--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: [XCG815]  Estimated peak HBM usage (26.537GB) exceeds 24GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
+2025-11-27T15:03:49Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815]  Estimated peak HBM usage (26.537GB) exceeds 24GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
+

neuronxcc-2.21.18209.0+043b1bf7/MODULE_8325de44f605a823c436+a32116a7/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_8325de44f605a823c436+a32116a7/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0a3e441a854ee41a2276c1518609fd4d76b0243a9324305bc07d8cd8d64d6fa1
+size 309218022

neuronxcc-2.21.18209.0+043b1bf7/MODULE_8325de44f605a823c436+a32116a7/model.log

@@ -0,0 +1,3 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_8325de44f605a823c436+a32116a7.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding/_tp0_bk0/model.MODULE_8325de44f605a823c436+a32116a7.neff', '--target=trn2', '--auto-cast=none', '--model-type=transformer', '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ', '-O2', '--lnc=2', '--logfile=/tmp/nxd_model/context_encoding/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: [XCG815]  Estimated peak HBM usage (29.349GB) exceeds 24GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
+2025-11-27T12:18:44Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815]  Estimated peak HBM usage (29.349GB) exceeds 24GB. Neff might be unable to load on chip. If you believe this estimation to be inaccurate, you can disable the check using: `--internal-backend-options=' --disable-hbm-usage-check '` - Please open a support ticket at https://github.com/aws-neuron/aws-neuron-sdk/issues/new. You may also be able to obtain more information using the 'XLA_IR_DEBUG' and 'XLA_HLO_DEBUG' environment variables.
+

neuronxcc-2.21.18209.0+043b1bf7/MODULE_a42f0ea98535622da192+ac10809c/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_a42f0ea98535622da192+ac10809c/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608a242d7b2e8f63eb7fc01a96237daf8141e54c737fa3029ceaab5aaf2b66ec
+size 304936914

neuronxcc-2.21.18209.0+043b1bf7/MODULE_a42f0ea98535622da192+ac10809c/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84fba4d0937a4e0d98003e8309115635db8e7521dbde620a3095507f85d1edc1
+size 15391744

neuronxcc-2.21.18209.0+043b1bf7/MODULE_a42f0ea98535622da192+ac10809c/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b13c9403176a2f84027601bf46e9f78dd3528b386784e9e054515646492279
+size 15701093

neuronxcc-2.21.18209.0+043b1bf7/MODULE_b50fd34438465c143456+ac10809c/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn2", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=2", "--logfile=/tmp/nxd_model/token_generation/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.21.18209.0+043b1bf7/MODULE_b50fd34438465c143456+ac10809c/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09751a30b4f4a733f9b2e3ea959d6e13a475daa18e9b00c87827261fa81d928c
+size 103598913

neuronxcc-2.21.18209.0+043b1bf7/MODULE_b50fd34438465c143456+ac10809c/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59380a9125d65a7774945e905d0ad89cff759e65ac2e5f479fff373ad9e0edc
+size 7169024

neuronxcc-2.21.18209.0+043b1bf7/MODULE_b50fd34438465c143456+ac10809c/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:292d6ce7151d25e424cb3eb49a31e99b915adacc4129a08d870c6744a6012c77
+size 7478373