Synchronizing local compiler cache.

.gitattributes

@@ -2733,3 +2733,50 @@ neuronxcc-2.17.194.0+d312836f/MODULE_0191a5f7284b00665cc0+613edded/model.neff fi
 neuronxcc-2.17.194.0+d312836f/MODULE_15ff576e3081c9564b48+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_9c8fcd1797ad84745497+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_ea55ff0c585401f8acb5+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_22cf23062ec53b3fd95d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_284ddd1b388e504631b8+ee23c5ad/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_2ef52130792b59d66c66+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_3cd14d7a79a82df7bd50+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_3da832fdaa3d62981800+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_3e665c1a4dd32437e7a0+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_40a0e75a65ac51fdd01a+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_51d9fed86504dfbff43c+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_5368928916623911b1f2+84f3e719/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_54cb17f251d5b78afb71+6e42245d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_5c17a6fec29c60d2f8a5+6e42245d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_7255935f4f53054509f6+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_73a8fcccb40e156a3330+6e42245d/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_788eb0c6a9b0ca759eca+5be477de/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_828dd739430ebe2df536+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_8c063f8f288a908bf850+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_913f4e1e2b4632438fe9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_b811ebc7b9aa6e1eb84f+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_c49c0c3715f68c22b32f+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_cd4240e56f3558bf8cf0+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_cf41a32ef696654dc19b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_d06255807e916c398b05+ee23c5ad/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_de8368a717cfd6dfec57+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_df48af4bf01af7f3857e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_e0765cf6df2204e3664e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_e36f587c697c4d8df3f6+ee23c5ad/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_e9bcfc17d832317203bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_f91cd98a64f373af274d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.18.121.0+9e31e41a/MODULE_fda7fb53c475ba393ed7+613edded/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/04f1740b7a0d1c756d80.json

@@ -0,0 +1,51 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+  "_task": "text-generation",
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 1.0,
+  "embedding_multiplier": 1.0,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "logits_scaling": 1.0,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "bf16",
+    "batch_size": 1,
+    "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+    "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": true,
+    "group_query_attention": null,
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 49152
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/6ae95ac44a666f05c6ac.json

@@ -0,0 +1,51 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+  "_task": "text-generation",
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 1.0,
+  "embedding_multiplier": 1.0,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "logits_scaling": 1.0,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 1,
+    "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+    "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": true,
+    "group_query_attention": null,
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 49152
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/d89e7bb9ce60e060a05a.json

@@ -0,0 +1,51 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+  "_task": "text-generation",
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attention_multiplier": 1.0,
+  "embedding_multiplier": 1.0,
+  "hidden_act": "silu",
+  "hidden_size": 32,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "logits_scaling": 1.0,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 2,
+    "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM",
+    "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5",
+    "collectives_layout": "HSB",
+    "continuous_batching": true,
+    "fuse_qkv": true,
+    "group_query_attention": null,
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "residual_multiplier": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 49152
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/0a43825be7b7281911e9.json

@@ -0,0 +1,77 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 2,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "continuous_batching": true,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 2,
+    "max_context_length": 100,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 100,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "float16",
+    "sequence_length": 100,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "float16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/22733839dacb6e5015cd.json

@@ -0,0 +1,77 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 100,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 100,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 100,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/7e0883804eb67213ba2d.json

@@ -0,0 +1,55 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "BSH",
+    "attn_output_transposed": false,
+    "auto_cast_type": "bf16",
+    "batch_size": 1,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": true,
+    "group_query_attention": null,
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/8092f01dcffbf2d4dd15.json

@@ -0,0 +1,55 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "BSH",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 1,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": true,
+    "group_query_attention": null,
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/ee3839ec4d870a814ca2.json

@@ -0,0 +1,55 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "BSH",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 2,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "collectives_layout": "HSB",
+    "continuous_batching": true,
+    "fuse_qkv": true,
+    "group_query_attention": null,
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/llamafactory/tiny-random-Llama-3/f703f2db24b888540de0.json

@@ -0,0 +1,77 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "llamafactory/tiny-random-Llama-3",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 4,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 64,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "llamafactory/tiny-random-Llama-3",
+    "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": true,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 100,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 100,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "float16",
+    "sequence_length": 100,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "float16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/llama/unsloth/Llama-3.2-1B-Instruct/ba8db5c1f8497571a448.json

@@ -0,0 +1,56 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "unsloth/Llama-3.2-1B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "BSH",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 4,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "collectives_layout": "HSB",
+    "continuous_batching": true,
+    "fuse_qkv": true,
+    "group_query_attention": "shard-over-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 4096,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "unsloth_fixed": true,
+  "use_cache": true,
+  "vocab_size": 128256
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/9dc90635cfa8c5b914cc.json

@@ -0,0 +1,73 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "dacorvo/Mixtral-tiny",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 1024,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 2,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "dacorvo/Mixtral-tiny",
+    "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 2,
+    "max_context_length": 100,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 100,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "float16",
+    "sequence_length": 100,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "float16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32000
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/adc2150036a52ffc6af5.json

@@ -0,0 +1,73 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "dacorvo/Mixtral-tiny",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 1024,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "dacorvo/Mixtral-tiny",
+    "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 100,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 100,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 100,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32000
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/mixtral/dacorvo/Mixtral-tiny/b05741f94b766070c26a.json

@@ -0,0 +1,73 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "dacorvo/Mixtral-tiny",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "head_dim": 32,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 1024,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "dacorvo/Mixtral-tiny",
+    "checkpoint_revision": "c557ba205ddff6ea911f4719e0d543d6c08356b6",
+    "continuous_batching": false,
+    "enable_bucketing": false,
+    "ep_degree": 1,
+    "flash_decoding_enabled": false,
+    "fused_qkv": false,
+    "glu_mlp": true,
+    "is_chunked_prefill": false,
+    "local_ranks_size": 2,
+    "logical_nc_config": 1,
+    "max_batch_size": 1,
+    "max_context_length": 100,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 100,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "float16",
+    "sequence_length": 100,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 0,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "float16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32000
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/93d1c70697961dfb4051.json

@@ -0,0 +1,52 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/phi-4-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {},
+  "embd_pdrop": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": false,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 2,
+    "checkpoint_id": "yujiepan/phi-4-tiny-random",
+    "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
+    "collectives_layout": "HSB",
+    "continuous_batching": true,
+    "fuse_qkv": true,
+    "group_query_attention": "replicated-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "original_max_position_embeddings": 16384,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 100352
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/dd7372422bdfe51f7483.json

@@ -0,0 +1,52 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/phi-4-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {},
+  "embd_pdrop": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": false,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 1,
+    "checkpoint_id": "yujiepan/phi-4-tiny-random",
+    "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": true,
+    "group_query_attention": "replicated-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "original_max_position_embeddings": 16384,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 100352
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/phi3/yujiepan/phi-4-tiny-random/f40bbae82fb4cfd892b6.json

@@ -0,0 +1,52 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/phi-4-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {},
+  "embd_pdrop": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 32,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": false,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "bf16",
+    "batch_size": 1,
+    "checkpoint_id": "yujiepan/phi-4-tiny-random",
+    "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": true,
+    "group_query_attention": "replicated-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 1,
+  "original_max_position_embeddings": 16384,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 100352
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/21462d921fe00fab6cf6.json

@@ -0,0 +1,53 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 16,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 1,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 1,
+    "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
+    "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": false,
+    "group_query_attention": "shard-over-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/5ec3ea4c38639645de5e.json

@@ -0,0 +1,53 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 16,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 1,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "bf16",
+    "batch_size": 1,
+    "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
+    "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
+    "collectives_layout": "HSB",
+    "continuous_batching": false,
+    "fuse_qkv": false,
+    "group_query_attention": "shard-over-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

neuronxcc-2.18.121.0+9e31e41a/0_REGISTRY/0.2.0.dev7/qwen2/yujiepan/qwen2.5-128k-tiny-random/ad4d2aee22289a920d76.json

@@ -0,0 +1,53 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "yujiepan/qwen2.5-128k-tiny-random",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 8,
+  "initializer_range": 0.02,
+  "intermediate_size": 16,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 1,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "HloNeuronConfig",
+    "all_reduce_dtype": null,
+    "allow_flash_attention": true,
+    "attention_layout": "HSB",
+    "attn_output_transposed": false,
+    "auto_cast_type": "fp16",
+    "batch_size": 2,
+    "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random",
+    "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0",
+    "collectives_layout": "HSB",
+    "continuous_batching": true,
+    "fuse_qkv": false,
+    "group_query_attention": "shard-over-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.18.121.0+9e31e41a",
+    "optimum_neuron_version": "0.2.0.dev7",
+    "output_all_logits": false,
+    "sequence_length": 100,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 4,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "original_max_position_embeddings": 32768,
+    "rope_type": "yarn",
+    "type": "yarn"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.18.121.0+9e31e41a/MODULE_0672b5f56c1c30461234+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812e7533a893b01d4889fd56aed08a4d04c176a543db1294b6993942845906cc
+size 7106

neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.18.121.0+9e31e41a/MODULE_088cee8e523341202b27+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbb43375f225e75f29624572006b6531f223eb07afc06f0f084b46ef315750fc
+size 7106

neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/token_generation_model/_tp0_bk0/log-neuron-cc.txt", "--enable-internal-neff-wrapper"]

neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee8ff96a09e7f8b2d0e01617ec7d0fb75c815a76a68ec40016def33bf974af7
+size 80428

neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bdbcb91e1b29691ae1ec050e5a4fd31fc9ba2475ffeea46b71b571b880a994d
+size 236544

neuronxcc-2.18.121.0+9e31e41a/MODULE_0d49ee5986eac20aedab+5be477de/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137567311745b944d4e98177aec0d5d879f138f88e9298aa007003bce0d3734a
+size 244319

neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/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-dge-dma --vectorize-strided-dma ", "-O2", "--internal-num-neuroncores-per-sengine=1", "--logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"]

neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cee9957eb134e14bbaa4c3c7b989176a02ef262107f354f444b1a2bd85e3c438
+size 80388

neuronxcc-2.18.121.0+9e31e41a/MODULE_139ec5f0b454074217c8+84f3e719/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6654cb47676a5dda37938e1c3b91dfabe8a6445dd8a1d9ae0f7e5b66a2cca6a1
+size 226304

neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:206a7ad89370cff8d2b2322c1ac670c89f032f09dacf78c1919f6862a5f988f8
+size 20204

neuronxcc-2.18.121.0+9e31e41a/MODULE_1649fc77b87fff02e370+613edded/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1097368aaa1ce8526d2e6e5468918bec01b472641e3929c5ef405dce6a8a9625
+size 134144

neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/compile_flags.json

@@ -0,0 +1 @@
+"--model-type=transformer -O1 --lnc=1 --internal-hlo2tensorizer-options=--experimental-unsafe-fp8e4m3fn-as-fp8e4m3 --logfile=/tmp/nxd_model/layout_opt/log-neuron-cc.txt"

neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bcdec06d89d654845d062183036a3a4b545c119ab7f8bfcfcf806a54b9b35d
+size 11183

neuronxcc-2.18.121.0+9e31e41a/MODULE_18642e0fd797db5b7fcb+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15bf257da8d2ac9c165a0f254170c9fcf42921fe07da2394a99317acf58d9a53
+size 103424

neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]

neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3978ae0dae4598ee8e9bbe8392fc2e7e13757206db58da945eeacc59ca5ff3de
+size 21402

neuronxcc-2.18.121.0+9e31e41a/MODULE_1b80b788e3a49498f963+613edded/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb0f3d36d810f920a63f120e7d5fd467d839408f2db5720ef1c3a224807664f
+size 144384

neuronxcc-2.18.121.0+9e31e41a/MODULE_1df250ef1cf7a7de560f+613edded/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"]