diff --git a/.gitattributes b/.gitattributes
index 04667736dc887792210f479fd1961d83d9b3acc0..4028424f7d0bece022538c07607a5f6a015abbbe 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -8436,3 +8436,10 @@ neuronxcc-2.17.194.0+d312836f/MODULE_eb6d7bd59bec7840dd72+bfe5714b/model.neff fi
 neuronxcc-2.17.194.0+d312836f/MODULE_f1f84223fca9c333bb2f+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_f37bc22c32c557b09691+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_f37bc22c32c557b09691+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/05c9cb13b974d4bfbb70.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/05c9cb13b974d4bfbb70.json
new file mode 100644
index 0000000000000000000000000000000000000000..ef86a8ee1da12eb67729306ca3e4d59bd16b627f
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/05c9cb13b974d4bfbb70.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/182f570e395a76ac2d2c.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/182f570e395a76ac2d2c.json
new file mode 100644
index 0000000000000000000000000000000000000000..37451622c88415313cc5b2f1e323877c998acc3c
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/182f570e395a76ac2d2c.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/7def1dfbe4c4fd9f87fd.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/7def1dfbe4c4fd9f87fd.json
new file mode 100644
index 0000000000000000000000000000000000000000..05bf64337625dabccb1ac434b56f688a7dffe6f4
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/7def1dfbe4c4fd9f87fd.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/081c145e831213ab718b.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/081c145e831213ab718b.json
new file mode 100644
index 0000000000000000000000000000000000000000..7fe79c7e65da7d22ba842889052c453dd413b49a
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/081c145e831213ab718b.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": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/087436195a7333857a9f.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/087436195a7333857a9f.json
new file mode 100644
index 0000000000000000000000000000000000000000..4caec6d84ab4065206865cb35990a7171b6184cf
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/087436195a7333857a9f.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": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/2308b99b68d27ecfdc41.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/2308b99b68d27ecfdc41.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff7776b8353ef5219b701815c63d2503f720904b
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/2308b99b68d27ecfdc41.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": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/2c27b201142fed60ee5b.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/2c27b201142fed60ee5b.json
new file mode 100644
index 0000000000000000000000000000000000000000..e796f6e0d3838cab1abc9eb3e08f2e0096ad7dd0
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/2c27b201142fed60ee5b.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/304cd41ac7d9c2303bd3.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/304cd41ac7d9c2303bd3.json
new file mode 100644
index 0000000000000000000000000000000000000000..df65401a77e7399f56d6813ca1fa48a2cf7d5a08
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/304cd41ac7d9c2303bd3.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/7f5cf6b207ab7e9d6384.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/7f5cf6b207ab7e9d6384.json
new file mode 100644
index 0000000000000000000000000000000000000000..4367543e5e7e98e21aff9c34320b88393331e8ac
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/llamafactory/tiny-random-Llama-3/7f5cf6b207ab7e9d6384.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/5e144164d13014b24277.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/5e144164d13014b24277.json
new file mode 100644
index 0000000000000000000000000000000000000000..8b22c9a1b4604171901cc270a00f5d5e2dbf897d
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/5e144164d13014b24277.json
@@ -0,0 +1,78 @@
+{
+  "_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": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 4,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": "5a8abab4a5d6f164389b1079fb721cfab8d7126c",
+    "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": 4,
+    "max_context_length": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "float16",
+    "sequence_length": 4096,
+    "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_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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/60969fb571a659b30503.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/60969fb571a659b30503.json
new file mode 100644
index 0000000000000000000000000000000000000000..638e16e2ec88da9a4c7331cea7f09ef4f941a06b
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/60969fb571a659b30503.json
@@ -0,0 +1,78 @@
+{
+  "_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": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": null,
+    "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": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 4096,
+    "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_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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/c8d149891550d3793bb9.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/c8d149891550d3793bb9.json
new file mode 100644
index 0000000000000000000000000000000000000000..f90588ec94319065b90d7e9fb00655fb562f8053
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/llama/unsloth/Llama-3.2-1B-Instruct/c8d149891550d3793bb9.json
@@ -0,0 +1,78 @@
+{
+  "_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": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "unsloth/Llama-3.2-1B-Instruct",
+    "checkpoint_revision": null,
+    "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": 4096,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 4096,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 4096,
+    "sequence_parallel_enabled": false,
+    "speculation_length": 5,
+    "start_rank_id": 0,
+    "target": null,
+    "torch_dtype": "bfloat16",
+    "tp_degree": 2,
+    "vocab_parallel": false
+  },
+  "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/4e14b2bd4d311cf1902f.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/4e14b2bd4d311cf1902f.json
new file mode 100644
index 0000000000000000000000000000000000000000..07b9249aafe639683bf3be7b242194599deace1b
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/4e14b2bd4d311cf1902f.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": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/7d7a8f9e25ad161672e4.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/7d7a8f9e25ad161672e4.json
new file mode 100644
index 0000000000000000000000000000000000000000..e42d98c056a12e406af62bddea005914d7bd6c0e
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/7d7a8f9e25ad161672e4.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": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/fa8340534c295e77e3b6.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/fa8340534c295e77e3b6.json
new file mode 100644
index 0000000000000000000000000000000000000000..cc3d3a922c52bfd4fc0ccee6cb8012f0aba97d56
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/mixtral/dacorvo/Mixtral-tiny/fa8340534c295e77e3b6.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": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": false,
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/732f0a646f3fead04cc6.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/732f0a646f3fead04cc6.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c5a515bbd195226d0332b6eb5ad516b047de3c7
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/732f0a646f3fead04cc6.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/dd2dd68e4186f608717a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/dd2dd68e4186f608717a.json
new file mode 100644
index 0000000000000000000000000000000000000000..159032fed683628da60f0d9764c1d9b666f0c4db
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/dd2dd68e4186f608717a.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/ebcb161fd1f8a2eaaf0a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/ebcb161fd1f8a2eaaf0a.json
new file mode 100644
index 0000000000000000000000000000000000000000..fb74d72ac7d483826fa0e067f571b3493600cd09
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/phi3/yujiepan/phi-4-tiny-random/ebcb161fd1f8a2eaaf0a.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/Qwen/Qwen2.5-0.5B/1454002290e6730d8902.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/Qwen/Qwen2.5-0.5B/1454002290e6730d8902.json
new file mode 100644
index 0000000000000000000000000000000000000000..d3d6c383b345f55d8ab8f3c82a639094e0cabc71
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/Qwen/Qwen2.5-0.5B/1454002290e6730d8902.json
@@ -0,0 +1,49 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "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": 4,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "collectives_layout": "HSB",
+    "continuous_batching": true,
+    "fuse_qkv": false,
+    "group_query_attention": "shard-over-heads",
+    "log_softmax_scores": false,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "output_all_logits": false,
+    "sequence_length": 4096,
+    "tp_degree": 2
+  },
+  "num_attention_heads": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/7823ff8dffd276c75ce4.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/7823ff8dffd276c75ce4.json
new file mode 100644
index 0000000000000000000000000000000000000000..257811965ae23d2e5d1f2a14a37873ffc88d7a4f
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/7823ff8dffd276c75ce4.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/d8e67fd7c8f8e393dc42.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/d8e67fd7c8f8e393dc42.json
new file mode 100644
index 0000000000000000000000000000000000000000..5d1ce000b3b074f70f537624342ae76de5dff14f
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/d8e67fd7c8f8e393dc42.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/f245d59e6049a5b7842a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/f245d59e6049a5b7842a.json
new file mode 100644
index 0000000000000000000000000000000000000000..05b5ff6949a78beb28f565fc19c0671720156271
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0/qwen2/yujiepan/qwen2.5-128k-tiny-random/f245d59e6049a5b7842a.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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0",
+    "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
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/d2572e7c03f09047aa6c.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/d2572e7c03f09047aa6c.json
new file mode 100644
index 0000000000000000000000000000000000000000..7f8e4466b264cea711a2ac1fe81dd908177e1f2c
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/qwen2/Qwen/Qwen2.5-0.5B/d2572e7c03f09047aa6c.json
@@ -0,0 +1,71 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "Qwen/Qwen2.5-0.5B",
+  "_task": "text-generation",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "hidden_act": "silu",
+  "hidden_size": 896,
+  "initializer_range": 0.02,
+  "intermediate_size": 4864,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 24,
+  "model_type": "qwen2",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 1,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "Qwen/Qwen2.5-0.5B",
+    "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987",
+    "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": 128,
+    "max_topk": 256,
+    "mlp_kernel_enabled": false,
+    "mlp_kernel_fuse_residual_add": false,
+    "n_active_tokens": 128,
+    "neuronxcc_version": "2.17.194.0+d312836f",
+    "num_cores_per_group": 1,
+    "on_device_sampling": true,
+    "optimum_neuron_version": "0.3.0.dev0",
+    "output_logits": false,
+    "padding_side": "right",
+    "pp_degree": 1,
+    "qk_layernorm": false,
+    "qkv_kernel_enabled": false,
+    "rpl_reduce_dtype": "bfloat16",
+    "sequence_length": 128,
+    "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": 14,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/compile_flags.json
@@ -0,0 +1 @@
+"--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"
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5c2b0d11e710c0c07ba16aef223dfff9a39f38dc
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cb48e74dbeaafb58771e45b6d0b36e41454443bf74bf0695899909b9dc170f1
+size 86903
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..6bbace6db800d0a03bd8a547bfd904bee40f2d31
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1e68e361d8fb5e36eac16d440957c4f5e4bef7149005ab3900ae8fb702be76e
+size 267264
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..9398659fd0e42f625e9c5ffffd5364ed795ba32a
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_306e43064416feb5de44+165e9558/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:357a75efd755e85350572569c6c48811082802b6ee3759554db1c834f2c345c9
+size 276419
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+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"
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..9f229eaf151b4568887dc08e4dd9043a74771c4a
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac926c6dd51d86cf6a76e668ff035fbbcedb1769803a4e4b4c802af52ec03de2
+size 8648
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..e2aa211cce69742e6f06f94b9a884d25fb2c1cab
Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_3678b7fe58e0d712139a+431f5505/model.neff differ
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/compile_flags.json
@@ -0,0 +1 @@
+"--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"
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..67e53eac10a6eef0d5fdf9db45b8a104095c8059
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ffbf0bb377b4db400d4ac37a60449bf98f88f3abe14a23cc93b4dfbfb30c8a3
+size 88689
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..7e8ef36330f145e330815eb4f0fe50b1d1a1c9ba
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3d29f316a0cedf338ff9+bfe5714b/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc1229629f4fe60e90fe49941317a7311410a6bf20a39522e45c41d59a5ba2a5
+size 257024
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/compile_flags.json
@@ -0,0 +1 @@
+"--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"
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..aacc4bd5830c6bb7c1b1099334d9da544c96f003
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728d79f343323eb8bf010275d0c930e634a26c255205106247fd693a5476cf90
+size 682084
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..0808c045080591de838abe640794972cb409442b
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362d3180cc3640ab47f60e2e2dbc3f898ee3b1ec6ab2a0f0defdf757bc966bc2
+size 1086464
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/wrapped_neff.hlo
new file mode 100644
index 0000000000000000000000000000000000000000..37b9f9eab90369e1e12e1b720496a5e9af3c3913
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_539052c00a259705e67b+165e9558/wrapped_neff.hlo
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8731e4eaad0abbc99fe7ec0a91150c589eefca01ca7f8d443a27c2364a0044b9
+size 1231490
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.hlo_module.pb
index 69b9e4248e41c5b70df9febd3bbb79369bdd5ab6..22ed5fafd8bbcf75aeb528d14e6823a0db3131d8 100644
--- a/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.hlo_module.pb
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.hlo_module.pb
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f71737f6ba0cf30a1390228ae07d8b66e24511de80060bfdeb9681627e258714
+oid sha256:4000a55e4f5dbd1eca9566ff60f1bf9acb1bc00e35f71e7a22220e1b5e977684
 size 81486
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.neff
index 0e037d1380da1beccb48e2d47b47026d1b61bcbd..c6b0095526b524d00f090f649914152acb083a46 100644
--- a/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.neff
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:301a92fbee06b6cc0a6021a0f3971876885e894feb84134dee23330484df95ed
+oid sha256:fda983457f78de472af959d6a4efea929f84f621f853fb5e08ad31af5af251b3
 size 318464
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/wrapped_neff.hlo
index 4dfd5190348f205f9527d3c43960ac1a75844e91..cb0413375448d9ce86351e0c0f3f487111664783 100644
--- a/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/wrapped_neff.hlo
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6b226c5a27dcc0947566+bfc62e4c/wrapped_neff.hlo
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7355e73d423890bb78057da1083c86320b3d4f862d2e6456f9914d9b0b267a14
+oid sha256:331f4ffb1d6e3629bb5003aa1cd32632d430b5e262306d5b1cb1a87610bcd14e
 size 329762
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.hlo_module.pb
index 6b5916448cbc71c71523c75f2859347818ebdb22..ca534c2b062cfc213ee53a6bb469955926de3538 100644
--- a/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.hlo_module.pb
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.hlo_module.pb
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420670e90420f71cc3b79c9680ccf8db2d2d3cb005ab48b09b9b70be64ce1736
+oid sha256:99959d517b441937c4fe7e78cd58d5e7ab0cdb4c53b3e466bbfa1712ad58ff0a
 size 82168
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.neff
index 09e9b6cecea04ac63da18c6ae751dd32e5aaa608..2378176dbf1213c35430882b63905261f2252038 100644
--- a/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.neff
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_73a8fcccb40e156a3330+26ac6be0/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d76404fcf0d7565b068d4d3f3ad427e2772eb8fd793b70381263a008d6fd25
+oid sha256:ddffdeed53d210d00069356f58e0f87bbf716ad1d2b87cd9f149b0506071b80b
 size 420864
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.neff
index 915a94677457f4ca7093e8003ee3e1457e04f044..7cf5beb59a199466b8988282ab6ab0d27a1f5b77 100644
--- a/neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.neff
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_bfedca8ab047e39c175b+431f5505/model.neff
@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac7b72ccc170f7d3c7ecf3395323f73bb336f90f5c9a351b43904b7b9cf462f
+oid sha256:d2f8209490daedb50f0809528a0f4f4b512ee9b2a4d690d986a8cf30b1c22aad
 size 103424
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+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"
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..88a92aa1c0289ebf9bdc2d1019575b6c3e0dcc50
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b6e5a21c39ea698391f4aa9d8270be9c63a60df066a26e13dfc4ddbea88c6f6
+size 149919
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..b35c7715a1f6485b88ce334b6af63eee880e65c1
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c04d3b7cb6b6f3e9f034+431f5505/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f31e734d988be9bf1305f07cf70a2bf9234d7ec5a8347dfc9e0a51f49e823f6f
+size 594944
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/compile_flags.json
new file mode 100644
index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/compile_flags.json
@@ -0,0 +1 @@
+"--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"
\ No newline at end of file
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.done
new file mode 100644
index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.hlo_module.pb
new file mode 100644
index 0000000000000000000000000000000000000000..5f0fb2ec41d5d1a57f0c50abbe18ceceb41448c2
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.hlo_module.pb
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f390d15097e2d8b3278540da26fabd071ac6bfeb17e5f2c17a4a9dcdd7587390
+size 633190
diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.neff
new file mode 100644
index 0000000000000000000000000000000000000000..368975bdb86554fc5d228dc06b451d03763ffbb5
--- /dev/null
+++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cac63cedabffb220b365+bfe5714b/model.neff
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bc8af0246160ded25d5d2241293b389352d65a6ecd4537a6d07964a505f674
+size 1147904