Synchronizing local compiler cache.

.gitattributes

@@ -10936,3 +10936,19 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_aa6b654bd981334a723e+a9d440f5/wrapped_neff
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_5cdc2024ee2e6c48bd40+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_5cdc2024ee2e6c48bd40+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ca134f082760cd304e7+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_02da278f167522769f43+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_31248f3f93aafaf6dbaa+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_31248f3f93aafaf6dbaa+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_3cbaae1c02abefd7f494+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_3cbaae1c02abefd7f494+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_43116d82b5805ba3ae20+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_43116d82b5805ba3ae20+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ab214a26135c9602b57+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ddd5b729b9e4ecede70+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ddd5b729b9e4ecede70+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_bbb0c02d6e06f337e549+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_d0af99bdae3af4d95a22+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_d0af99bdae3af4d95a22+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_e5e262df0f4573dfd367+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_efa7fe965caa79aca41c+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_efa7fe965caa79aca41c+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama4_text/meta-llama/Llama-4-Scout-17B-16E-Instruct/5c9a7ddb696911cf7f93.json

@@ -0,0 +1,221 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+  "_task": "text-generation",
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": true,
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 1,
+  "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": 10485760,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40,
+    41,
+    42,
+    43,
+    44,
+    45,
+    46,
+    47
+  ],
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+    "checkpoint_revision": "92f3b1597a195b523d8d9e5700e57e4fbb8f20d3",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 16,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.3.1.dev6",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 16
+  },
+  "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": 16,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 16.0,
+    "high_freq_factor": 1.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "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": true,
+  "vocab_size": 202048
+}

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/llama4_text/meta-llama/Llama-4-Scout-17B-16E-Instruct/f9d1010b22a4e5da4bd5.json

@@ -0,0 +1,221 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+  "_task": "text-generation",
+  "attention_bias": false,
+  "attention_chunk_size": 8192,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": true,
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 1,
+  "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": 10485760,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    0,
+    1,
+    2,
+    3,
+    4,
+    5,
+    6,
+    7,
+    8,
+    9,
+    10,
+    11,
+    12,
+    13,
+    14,
+    15,
+    16,
+    17,
+    18,
+    19,
+    20,
+    21,
+    22,
+    23,
+    24,
+    25,
+    26,
+    27,
+    28,
+    29,
+    30,
+    31,
+    32,
+    33,
+    34,
+    35,
+    36,
+    37,
+    38,
+    39,
+    40,
+    41,
+    42,
+    43,
+    44,
+    45,
+    46,
+    47
+  ],
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+    "checkpoint_revision": "92f3b1597a195b523d8d9e5700e57e4fbb8f20d3",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 16,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.1.dev6",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 16
+  },
+  "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": 16,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 16.0,
+    "high_freq_factor": 1.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "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": true,
+  "vocab_size": 202048
+}

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/qwen3_moe/Qwen/Qwen3-30B-A3B-Instruct-2507/0dd3b941d43fb01b72a8.json

@@ -0,0 +1,66 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+    "checkpoint_revision": "61082d4deaa4785f64943b443cbc2b5de7524fad",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 16,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.3.1.dev6",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 16
+  },
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/qwen3_moe/Qwen/Qwen3-30B-A3B-Instruct-2507/5c776e5f1eb55e76831a.json

@@ -0,0 +1,66 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "decoder_sparse_step": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 6144,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 48,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 768,
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 4,
+    "capacity_factor": null,
+    "checkpoint_id": "Qwen/Qwen3-30B-A3B-Instruct-2507",
+    "checkpoint_revision": "61082d4deaa4785f64943b443cbc2b5de7524fad",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 16,
+    "logical_nc_config": 1,
+    "max_batch_size": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.19.8089.0+8ab9f450",
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.1.dev6",
+    "output_logits": false,
+    "pp_degree": 1,
+    "sequence_length": 4096,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 16
+  },
+  "norm_topk_prob": true,
+  "num_attention_heads": 32,
+  "num_experts": 128,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 4,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/t5/hf-internal-testing/tiny-random-t5/15f7e443873c3474a6aa.json

@@ -0,0 +1,91 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-t5",
+  "_task": null,
+  "decoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_num_beams": 4,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  },
+  "encoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_num_beams": 4,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  }
+}

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/t5/hf-internal-testing/tiny-random-t5/5d5dadc2c2138bf8ab44.json

@@ -0,0 +1,91 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-t5",
+  "_task": null,
+  "decoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": true,
+      "output_hidden_states": true,
+      "static_batch_size": 1,
+      "static_num_beams": 1,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  },
+  "encoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": true,
+      "output_hidden_states": true,
+      "static_batch_size": 1,
+      "static_num_beams": 1,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  }
+}

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/t5/hf-internal-testing/tiny-random-t5/d83e395611ddc3a29d9f.json

@@ -0,0 +1,91 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-t5",
+  "_task": null,
+  "decoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_num_beams": 1,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  },
+  "encoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_num_beams": 1,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  }
+}

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev6/t5/hf-internal-testing/tiny-random-t5/e57cbde649dde732937d.json

@@ -0,0 +1,91 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-t5",
+  "_task": null,
+  "decoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": true,
+      "output_hidden_states": true,
+      "static_batch_size": 1,
+      "static_num_beams": 4,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  },
+  "encoder": {
+    "classifier_dropout": 0.0,
+    "d_ff": 37,
+    "d_kv": 8,
+    "d_model": 32,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "relu",
+    "dropout_rate": 0.1,
+    "feed_forward_proj": "relu",
+    "gradient_checkpointing": false,
+    "initializer_factor": 0.002,
+    "is_encoder_decoder": true,
+    "is_gated_act": false,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "disable_fallback": false,
+      "disable_fast_relayout": false,
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": true,
+      "output_hidden_states": true,
+      "static_batch_size": 1,
+      "static_num_beams": 4,
+      "static_sequence_length": 64,
+      "task": "text2text-generation",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 5,
+    "num_heads": 4,
+    "num_layers": 5,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 8,
+    "use_cache": true,
+    "vocab_size": 1103
+  }
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_02da278f167522769f43+253d6470/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", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_02da278f167522769f43+253d6470/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67438285964b08bb19d5cc976e3c54297f08d1b0df76c2f3fe542e1624483de2
+size 9670898

neuronxcc-2.19.8089.0+8ab9f450/MODULE_02da278f167522769f43+253d6470/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:851ad19d69a28aebcb76eeb4e4529f9d13bd810ffc4849ea085036f1af5e2beb
+size 17439744

neuronxcc-2.19.8089.0+8ab9f450/MODULE_15f7e443873c3474a6aa/decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b788d306aa621145bd4c1b566e270308aa9d03f560b54a659020c5087dc28413
-size 1190094
+oid sha256:c062fb6a1f3d277faac7225d1bec3b60dff7c9c7f780cc21ef74a345ad1e0409
+size 1189966

neuronxcc-2.19.8089.0+8ab9f450/MODULE_15f7e443873c3474a6aa/encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd726585ac540b16f29cf45b77f7fa0beb2fa5363f3d09a5a0c25c4007501304
-size 349882
+oid sha256:7c3b2291d6e1e91d862de919369aef0c73f10af7f0d3d06bdac64df2f247ceb8
+size 349818

neuronxcc-2.19.8089.0+8ab9f450/MODULE_234b5c34641e778cc5d2+ed72d204/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_234b5c34641e778cc5d2+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddfdd3b97bc014c3753edd934bfc9558878a8ef0a424799cec49b546e76cb5c8
+size 110959906

neuronxcc-2.19.8089.0+8ab9f450/MODULE_234b5c34641e778cc5d2+ed72d204/model.log

@@ -0,0 +1,3 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_234b5c34641e778cc5d2+ed72d204.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_234b5c34641e778cc5d2+ed72d204.neff', '--target=trn1', '--auto-cast=none', '--model-type=transformer', '--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ', '-O2', '--lnc=1', '--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: [XCG815]  Estimated peak HBM usage (18.327946) exceeds 16GB. Neff won't be able to load on chip - 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.
+2025-09-10T13:49:56Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815]  Estimated peak HBM usage (18.327946) exceeds 16GB. Neff won't be able to load on chip - 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-2.19.8089.0+8ab9f450/MODULE_31248f3f93aafaf6dbaa+cd3419b6/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", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_31248f3f93aafaf6dbaa+cd3419b6/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0058240e54b46c6b0db4c14f906f09f3ec484e7e04c3f2cb6e1f8eda3c5888d7
+size 2507590

neuronxcc-2.19.8089.0+8ab9f450/MODULE_31248f3f93aafaf6dbaa+cd3419b6/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74f90bab7cf259aea0daac2a556646ed4ff30addb7831a0a31f1a3b3cb58934
+size 3533824

neuronxcc-2.19.8089.0+8ab9f450/MODULE_31248f3f93aafaf6dbaa+cd3419b6/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd51c5d89811b2361e4f8267cb657832f235da127ac6940aed8e0a70761b6052
+size 3783895

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3cbaae1c02abefd7f494+a9d440f5/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3cbaae1c02abefd7f494+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12093b664d384d4f227211cf30520c33cb2f168bf18efd5680e7a6f0759e3946
+size 103130389

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3cbaae1c02abefd7f494+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fafff6c8809235ac7997becb99200b923ac6f9c9084ee79e97d7948b30d87e8f
+size 7803904

neuronxcc-2.19.8089.0+8ab9f450/MODULE_3cbaae1c02abefd7f494+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4013a9888058e7c0e8ac2ce33000d806be95273272575932d5e51e724e37a029
+size 8121064

neuronxcc-2.19.8089.0+8ab9f450/MODULE_43116d82b5805ba3ae20+cd3419b6/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", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_43116d82b5805ba3ae20+cd3419b6/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9b145a643ac4afcec643c5a4cf0003579212a43c2ea7b2cab1f7635446c3c40
+size 2458664

neuronxcc-2.19.8089.0+8ab9f450/MODULE_43116d82b5805ba3ae20+cd3419b6/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ecc4a985b50e6be447dcba49851f6869f4bc0661ddb70c5528f11b5a721ac0a
+size 3492864

neuronxcc-2.19.8089.0+8ab9f450/MODULE_43116d82b5805ba3ae20+cd3419b6/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b58e441608e9340359965eeeb8e0d0229dfbd7a847939c284e69325334c98780
+size 3742824

neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ab214a26135c9602b57+ed72d204/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ab214a26135c9602b57+ed72d204/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df61ac9ae7cc3b8d0b92f84adaaafb47ca0c3968defd912edc4a081cd7c233d6
+size 104317794

neuronxcc-2.19.8089.0+8ab9f450/MODULE_4ab214a26135c9602b57+ed72d204/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2632ba92083ecea71ec19ae561a0ca4e56249ffbd65c624502bc366b7b3cb3d4
+size 38933504

neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d5dadc2c2138bf8ab44/decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e7ed179c776a09dd00aaa5347656ca55f30a25cec07b7fbb278051a49788c69
-size 633172
+oid sha256:a9d1936dd388b9f965a4e1b24fedb24fb7c6a748789332d0d885bfbff8eded56
+size 633236

neuronxcc-2.19.8089.0+8ab9f450/MODULE_5d5dadc2c2138bf8ab44/encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bfc4ed25f9998aa656120620c0a3c0ce35bfc8aeefd672bc1695585a6bd1320
-size 351030
+oid sha256:12ca8cdd5d2f8186de84a66171ac1d9d021405c8a3c6b37c33e4945f018f175d
+size 351094

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ddd5b729b9e4ecede70+a9d440f5/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ddd5b729b9e4ecede70+a9d440f5/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a428bd8f83c4a722785ed440b47277011681572669d6eb5771db9d093585f13a
+size 104067050

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ddd5b729b9e4ecede70+a9d440f5/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d0fc0d34f44ca4b39e2257e2fc912b5d9662e0cf5c5772c7343dd108a85eef3
+size 11377664

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6ddd5b729b9e4ecede70+a9d440f5/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a48a1ffb1043c4f172ef65685fbbcae53db0a3670657a8f321d47245718a5a9
+size 11652584

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7557177e60b224d7d0cc+253d6470/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", "--internal-hlo2tensorizer-options=--verify-hlo=true", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7557177e60b224d7d0cc+253d6470/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2553215122056d902b1c55e7e737da5a9dafdc192698ac91c466be727a94caf7
+size 9674651

neuronxcc-2.19.8089.0+8ab9f450/MODULE_7557177e60b224d7d0cc+253d6470/model.log

@@ -0,0 +1,3 @@
+Failed compilation with ['neuronx-cc', 'compile', '--framework=XLA', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_7557177e60b224d7d0cc+253d6470.hlo_module.pb', '--output', '/tmp/nxd_model/context_encoding_model/_tp0_bk0/model.MODULE_7557177e60b224d7d0cc+253d6470.neff', '--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', '--internal-hlo2tensorizer-options=--verify-hlo=true', '--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt', '--verbose=35']: [XCG815]  Estimated peak HBM usage (17.053570) exceeds 16GB. Neff won't be able to load on chip - 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.
+2025-09-11T08:10:18Z Non-signal exit. Backend exited with code 1 and stderr: [XCG815]  Estimated peak HBM usage (17.053570) exceeds 16GB. Neff won't be able to load on chip - 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-2.19.8089.0+8ab9f450/MODULE_bbb0c02d6e06f337e549+ed72d204/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--auto-cast=none", "--model-type=transformer", "--tensorizer-options=--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2 --vectorize-strided-dma ", "-O2", "--lnc=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]