Synchronizing local compiler cache.

.gitattributes

@@ -4777,3 +4777,60 @@ neuronxcc-2.20.9961.0+0acef03a/MODULE_f68e835b3390768bbcce+5aef0af0/model.neff f
 neuronxcc-2.20.9961.0+0acef03a/MODULE_f68e835b3390768bbcce+5aef0af0/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.20.9961.0+0acef03a/MODULE_fdb7516de508e42d4f39+97633c67/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.20.9961.0+0acef03a/MODULE_fdb7516de508e42d4f39+97633c67/wrapped_neff.hlo 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_308ca0aab5adbc4e264e+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_308ca0aab5adbc4e264e+a9d440f5/wrapped_neff.hlo 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_63cd0b95d5730c3ea2ff+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_6972265ccbc24ff4448c+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_6972265ccbc24ff4448c+a9d440f5/wrapped_neff.hlo 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_6fcc6140d0bae101d7db+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_6fcc6140d0bae101d7db+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_7492a59ff398cdd8c726+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c3334ebde4334499745+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_826fd2949b06a672b9bc+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_8671664c95847cf8d9a7+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_8671664c95847cf8d9a7+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_88c363db429237aad147+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_8954b51aa51e21a41d91+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_8954b51aa51e21a41d91+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_91ccf5a53294ba164897+cd3419b6/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_91ccf5a53294ba164897+cd3419b6/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_96aa20706930df3658e1+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_96f456d652b2d2b5604f+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_96f456d652b2d2b5604f+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_978910d0b56af3a47501+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba467e042d35e9b674e+183b369f/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_9ba467e042d35e9b674e+183b369f/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_9dc23dbecde949377e19+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_9dc23dbecde949377e19+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_a8844fe97439b2667680+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_ae0fabd3d0b75f0150a0+253d6470/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_b576f2782b3f3348dc52+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_b576f2782b3f3348dc52+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_bd02c2f7c4741c76fe15+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_bd02c2f7c4741c76fe15+a9d440f5/wrapped_neff.hlo 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_d8d9690a1b9d2bd4cec3+87c2f0d1/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_d8d9690a1b9d2bd4cec3+87c2f0d1/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_db25850f47f3c97209ab+ed72d204/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_db7f53e8fbb89bd8136b+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_db7f53e8fbb89bd8136b+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_dbb440cbea65d345491d+e4fc2c3d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_dbb440cbea65d345491d+e4fc2c3d/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_dd67c7d76a4a3b7bc5ff+253d6470/model.neff 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/MODULE_fecd93fec248a64a0b00+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_fecd93fec248a64a0b00+a9d440f5/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/53100a81701818c9be88.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": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
+    "checkpoint_revision": "92f3b1597a195b523d8d9e5700e57e4fbb8f20d3",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 16,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "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/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/c958eda2360716f886e4.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": false,
+    "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/llama4_text/tiny-random/llama-4/585b1c34b9a47c8c0a73.json

@@ -0,0 +1,82 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "tiny-random/llama-4",
+  "_task": "text-generation",
+  "attention_bias": false,
+  "attention_chunk_size": 128,
+  "attention_dropout": 0.0,
+  "attn_scale": 0.1,
+  "attn_temperature_tuning": 4,
+  "cache_implementation": "hybrid",
+  "floor_scale": 8192,
+  "for_llm_compressor": false,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "interleave_moe_layer_step": 2,
+  "intermediate_size": 64,
+  "intermediate_size_mlp": 128,
+  "layer_types": [
+    "chunked_attention",
+    "chunked_attention",
+    "chunked_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 1048576,
+  "model_type": "llama4_text",
+  "moe_layers": [
+    1,
+    3
+  ],
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "batch_size": 1,
+    "capacity_factor": null,
+    "checkpoint_id": "tiny-random/llama-4",
+    "checkpoint_revision": "9e716f5d4d1ffe0a44a15f46f4a12b840439aba4",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 1024,
+    "max_topk": 256,
+    "n_active_tokens": 1024,
+    "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": 1024,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2
+  },
+  "no_rope_layers": [
+    1,
+    1,
+    1,
+    0
+  ],
+  "num_attention_heads": 1,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 4,
+  "num_key_value_heads": 1,
+  "num_local_experts": 8,
+  "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": true,
+  "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/qwen3_moe/Qwen/Qwen3-30B-A3B-Instruct-2507/99615150643a9e903722.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": 8,
+    "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": 8,
+    "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_00a086963636c3805778+ed72d204/model.hlo_module.pb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b6d089df781e3ab0dfe911812cbb200f2dc1d358cc2d49abd01f7222601b25
+oid sha256:52e2ac447c53f64b1d6c2ffa89ba1c66587cb89fa087c23a7f9e266d3953fca4
 size 497603

neuronxcc-2.19.8089.0+8ab9f450/MODULE_00a086963636c3805778+ed72d204/model.neff

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9cdaa16cfce3a4b868994f3a379ad2cc60becae6b12accc37ba0c6e7b5b89ad
+oid sha256:7d38dfb588e27e16a260ab31ca8eff6551c9655002dbe77ebf52baf8f9396af8
 size 31345664

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_10118825694329555156+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10118825694329555156+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a42e5d8e63342a8132a9098c06cceb024a7467006f87a370d54b32c22639217
+size 1584

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10149811978412508127+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10149811978412508127+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86311f9f0a00aedc439bf6b1a7e72130115305331deaa6d802b2852f929f1b25
+size 1584

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10449065838075029877+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10449065838075029877+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3772c9b53cf2c833d0d1c07c90e6b645617324394ad76cd3936137a547c93adf
+size 1144

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1054760819228113117+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1054760819228113117+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae138f6fc3e7b0cb4fdf2453c4cd8579723d427253d4f54a890b46ff7e1df6a
+size 1584

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10665707039599941067+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10665707039599941067+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48cdf21fbdf4fdcb05b1a22e95aee811e40354d8145c54198b487140629ca097
+size 1585

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10855235522929658999+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10855235522929658999+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eac431d89ac5d753c6c7948e2d74f830fde1dab9bf7d7cc89d1878ad7a29689a
+size 1146

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1090664928465068038+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_1090664928465068038+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e3e5d8a329342c24bbba2d50035e229e31a2376adb622342e9d86956cd7408a
+size 1584

neuronxcc-2.19.8089.0+8ab9f450/MODULE_11202137614579807680+e30acd3a/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1"]

neuronxcc-2.19.8089.0+8ab9f450/MODULE_11202137614579807680+e30acd3a/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a896dad3fa2c0fa6a2db99ab90c4b5edba1ae9ccb09ee00f41e99c511b14541
+size 1584