Synchronizing local compiler cache.

.gitattributes

@@ -8208,3 +8208,25 @@ neuronxcc-2.17.194.0+d312836f/MODULE_f358092e7338b2e4529f+7e4da68b/wrapped_neff.
 neuronxcc-2.17.194.0+d312836f/MODULE_f47f13ac4c1a1c792c33+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_f781291bf31bf79730b8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.17.194.0+d312836f/MODULE_f91cd98a64f373af274d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_098093605321e39067b1+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_22cf4b1c9280bdb27a84+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_3aaf2f909aa93d035b6b+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_3fa377f9222d3e733b57+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_48a1dea69e2dc2d09e06+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_48a1dea69e2dc2d09e06+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_4aa0e3bf1a6a1fb52787+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_638e58431e796ebec9da+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_81cb65755241019475b4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_aa317f69a340c77d5b24+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_aa317f69a340c77d5b24+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_ba7fb9c764ec187d8f06+26ac6be0/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_bcbb3942ae0e6e62f9ed+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_c1ff08289224c1071721+613edded/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_caf5f11d6a1c2af1a2d1+bfc62e4c/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_caf5f11d6a1c2af1a2d1+bfc62e4c/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_ed703e23be7449f8c891+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_ed703e23be7449f8c891+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_f2426656f5f2ceb6f048+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_f2426656f5f2ceb6f048+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_f2bc87b9df15b7784add+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.17.194.0+d312836f/MODULE_fdcbd41f965fdff93616+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/meta-llama/Llama-3.1-8B-Instruct/8261b9be41682c346506.json

@@ -0,0 +1,77 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "meta-llama/Llama-3.1-8B-Instruct",
+  "_task": "text-generation",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 32,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "meta-llama/Llama-3.1-8B-Instruct",
+    "checkpoint_revision": "0e9e39f249a16976918f6564b8830bc894c89659",
+    "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": 8,
+    "logical_nc_config": 1,
+    "max_batch_size": 32,
+    "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": true,
+    "optimum_neuron_version": "0.2.0.dev5",
+    "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": 8,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/acb8373c9ac1d7f31f35.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": "bf16",
+    "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": "2.17.194.0+d312836f",
+    "optimum_neuron_version": "0.2.0.dev5",
+    "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-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/e8f7b8c083bc968773ae.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": 8,
+    "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": true,
+    "optimum_neuron_version": "0.2.0.dev5",
+    "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": 8,
+    "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
+}

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/unsloth/Llama-3.2-1B-Instruct/fb7899d27ccbc59330a2.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.dev5",
+    "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
+}

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/mixtral/mistralai/Mixtral-8x7B-Instruct-v0.1/f96bf36952a158cc9e11.json

@@ -0,0 +1,73 @@
+{
+  "_entry_class": "SingleModelCacheEntry",
+  "_model_id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "_task": "text-generation",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "neuron": {
+    "_serialized_key": "NxDNeuronConfig",
+    "async_mode": false,
+    "attn_kernel_enabled": false,
+    "batch_size": 4,
+    "capacity_factor": null,
+    "cc_pipeline_tiling_factor": 2,
+    "checkpoint_id": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+    "checkpoint_revision": "41bd4c9e7e4fb318ca40e721131d4933966c2cc1",
+    "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": 16,
+    "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.dev5",
+    "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": 16,
+    "vocab_parallel": false
+  },
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "use_cache": true,
+  "vocab_size": 32000
+}

neuronxcc-2.17.194.0+d312836f/MODULE_098093605321e39067b1+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"

neuronxcc-2.17.194.0+d312836f/MODULE_098093605321e39067b1+bfe5714b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d8c682f938ff3b1b9b3c57138e1a5076e49c6e55c85df692d8d69af43a97b7
+size 445522

neuronxcc-2.17.194.0+d312836f/MODULE_098093605321e39067b1+bfe5714b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79f6c5a5b43cab2c955b06302c0df17da7b0f5a6746cdb45196262f10a38c702
+size 32072704

neuronxcc-2.17.194.0+d312836f/MODULE_22cf4b1c9280bdb27a84+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"

neuronxcc-2.17.194.0+d312836f/MODULE_22cf4b1c9280bdb27a84+bfe5714b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659bfaa3caeaf8610ec9442a59ee8e9fadb041133f90aaa310893d3076743607
+size 919265

neuronxcc-2.17.194.0+d312836f/MODULE_22cf4b1c9280bdb27a84+bfe5714b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:936afc71e5d663be56247d59efd97685b7d97e15ea16c901367ff64b6e1a4de2
+size 32646144

neuronxcc-2.17.194.0+d312836f/MODULE_3aaf2f909aa93d035b6b+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-2.17.194.0+d312836f/MODULE_3aaf2f909aa93d035b6b+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0732ce84be45cbbccd3553ef983356fc1a66fec1d645948ba5bd21ad3ed53959
+size 67559

neuronxcc-2.17.194.0+d312836f/MODULE_3aaf2f909aa93d035b6b+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08b6a54201f19df9a20d3431d8db484c2ea1680e561140e2a26725be7b7d2a5f
+size 338944

neuronxcc-2.17.194.0+d312836f/MODULE_3fa377f9222d3e733b57+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"

neuronxcc-2.17.194.0+d312836f/MODULE_3fa377f9222d3e733b57+bfe5714b/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:911683839345c4e7ccc7066521965c7158fe86de4be24320b0625bac3031c68a
+size 481775

neuronxcc-2.17.194.0+d312836f/MODULE_3fa377f9222d3e733b57+bfe5714b/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc320ba77bbd50659655c35d1bdb8b4d67489095f7367ee52198afe0c4186990
+size 9350144

neuronxcc-2.17.194.0+d312836f/MODULE_48a1dea69e2dc2d09e06+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"

neuronxcc-2.17.194.0+d312836f/MODULE_48a1dea69e2dc2d09e06+165e9558/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f661df1dc5c067ae27d14596c792d048e251e7a27b3a99b5e356e9083e29e35
+size 391520

neuronxcc-2.17.194.0+d312836f/MODULE_48a1dea69e2dc2d09e06+165e9558/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bad12a320939b96e8cb21672539a37646fda9d7c2f31df23d4f3b7cd66a587d
+size 1874944

neuronxcc-2.17.194.0+d312836f/MODULE_48a1dea69e2dc2d09e06+165e9558/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:154fe2edab408901eaf91c35a4f57c8329eeebaa0a4a8113a7e2d609c1c71f11
+size 1943827

neuronxcc-2.17.194.0+d312836f/MODULE_4aa0e3bf1a6a1fb52787+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-2.17.194.0+d312836f/MODULE_4aa0e3bf1a6a1fb52787+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:937307ec4fcd1402e9376652173dcf530be878628d31ce9638c8fd25c3f2a7a4
+size 69051

neuronxcc-2.17.194.0+d312836f/MODULE_4aa0e3bf1a6a1fb52787+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8b822ae4c28e96cec667246760be4e649c042e3e77064cb2f0db3229ceb574
+size 1158144

neuronxcc-2.17.194.0+d312836f/MODULE_638e58431e796ebec9da+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-2.17.194.0+d312836f/MODULE_638e58431e796ebec9da+431f5505/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d8f4c6678f640cbe18f7831799fb15955430608efef13668a3d24d0ec07d841
+size 68980

neuronxcc-2.17.194.0+d312836f/MODULE_638e58431e796ebec9da+431f5505/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea55f9825ecbb64ff8f748e4357261eecdd17674cd5df19f4c646f0f8a5b4b1
+size 615424

neuronxcc-2.17.194.0+d312836f/MODULE_81cb65755241019475b4+613edded/compile_flags.json

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

neuronxcc-2.17.194.0+d312836f/MODULE_81cb65755241019475b4+613edded/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9c706c65ac8e2d64843a198094d42a612c0a6950942e4ac69355368e1ccc19e
+size 233101

neuronxcc-2.17.194.0+d312836f/MODULE_81cb65755241019475b4+613edded/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b266b382dc7e7158631c934e443fab3230cff87b68bcc965dd8323ce4705b0c
+size 29062144

neuronxcc-2.17.194.0+d312836f/MODULE_aa317f69a340c77d5b24+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"

neuronxcc-2.17.194.0+d312836f/MODULE_aa317f69a340c77d5b24+165e9558/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63c4345aa7426dadf56657c2100e10b5b5f0681eb6af5462b439a3f779cf19b8
+size 776653

neuronxcc-2.17.194.0+d312836f/MODULE_aa317f69a340c77d5b24+165e9558/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:618238a62d08547235b590a1c74171b11f7e54df86fa66a100ac36a70e16121a
+size 6994944

neuronxcc-2.17.194.0+d312836f/MODULE_aa317f69a340c77d5b24+165e9558/wrapped_neff.hlo

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a8be3bad5d4226a5354995700d4891028bac71cf48535f5ffefdb29d7a39c52
+size 7132888

neuronxcc-2.17.194.0+d312836f/MODULE_ba7fb9c764ec187d8f06+26ac6be0/compile_flags.json

@@ -0,0 +1 @@
+"--enable-saturate-infinity --enable-mixed-precision-accumulation --model-type transformer -O1 --tensorizer-options='--enable-ccop-compute-overlap --cc-pipeline-tiling-factor=2' --internal-enable-dge-levels vector_dynamic_offsets --logfile=/tmp/nxd_model/context_encoding_model/_tp0_bk0/log-neuron-cc.txt"

neuronxcc-2.17.194.0+d312836f/MODULE_ba7fb9c764ec187d8f06+26ac6be0/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c77f0850f018366f7fa0bdadeea0b97f6a93b1c1b52602f2a50f922fae410e
+size 4802248

neuronxcc-2.17.194.0+d312836f/MODULE_ba7fb9c764ec187d8f06+26ac6be0/model.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21d738b1eb8e7c0c2fcc7a3d325d9a3c3a0c1a7344e3ee86d8aac48cb9f3eda
+size 9739264

neuronxcc-2.17.194.0+d312836f/MODULE_bcbb3942ae0e6e62f9ed+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"