diff --git a/.gitattributes b/.gitattributes index 357422c24729fe8243041a9869af437aeabcf3ea..d4ec5738c15fb9e1ea2d9af91ee680278ffc4839 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2353,3 +2353,20 @@ neuronxcc-2.17.194.0+d312836f/MODULE_8a1b493c9c28be330b53+7e4da68b/wrapped_neff. neuronxcc-2.17.194.0+d312836f/MODULE_953b5d662c5580b4b579+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.17.194.0+d312836f/MODULE_c0b1f40a34b7b2f5e74f+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text 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_0449610f6fd4f6f631e1+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/5cd8dc3fd87fbbb5bee6.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/5cd8dc3fd87fbbb5bee6.json new file mode 100644 index 0000000000000000000000000000000000000000..7fdd07bd374d7f5da5e783c14da2c82c20336a33 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/5cd8dc3fd87fbbb5bee6.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": 131072, + "max_topk": 256, + "mlp_kernel_enabled": false, + "mlp_kernel_fuse_residual_add": false, + "n_active_tokens": 131072, + "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": 131072, + "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.dev5/llama/llamafactory/tiny-random-Llama-3/b4c26214cb4b9de35645.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/b4c26214cb4b9de35645.json new file mode 100644 index 0000000000000000000000000000000000000000..41be769517c9937d61a171d6722e062842b647d1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/b4c26214cb4b9de35645.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": 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": "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.dev5/llama/llamafactory/tiny-random-Llama-3/edad95801000b2eb5ff8.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/edad95801000b2eb5ff8.json new file mode 100644 index 0000000000000000000000000000000000000000..617bc7eaf3c72d0cef8a7359eca36759e8a14cde --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev5/llama/llamafactory/tiny-random-Llama-3/edad95801000b2eb5ff8.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.dev5", + "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/MODULE_0449610f6fd4f6f631e1+793f1a96/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2d97ebfc93bd3ce3b26648c316a0ddb9ebae2f70 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/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 ' -O1 --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_0449610f6fd4f6f631e1+793f1a96/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..4791d130af9f8109b29e6bebf26d5d680a2c5474 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ff37e12281fa8f044284d20485952c2af497d3bb2bfcf50dd83e0572ef21aa4 +size 53031 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c72573bf7eaa7c712e08eec11936737b603fe090 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_0449610f6fd4f6f631e1+793f1a96/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bca18599ce5eec9b1297728172da2463337ab3ee0bbbb53457c2a8561f9305fe +size 213976064 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2d97ebfc93bd3ce3b26648c316a0ddb9ebae2f70 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/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 ' -O1 --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_194f7386f653405a01e3+793f1a96/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..c4854e080c49a63ceabc900490895c416012dbea --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74f43e3311b9d83a4aa162f61115cf21df7aeb47f9c912a5f4dcf725fe278d5a +size 84594 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fece9fb9c6bf1d0cd82251fc87a66ebbe7d79253 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_194f7386f653405a01e3+793f1a96/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4547ad6f958efc355d8e9f9d51bcf1cef08dc37ade07690de39371eea802d5b0 +size 226304 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+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_210699c2baa09235e112+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a4c575fedb2406e8ade30ce340cfb7e9baebde85 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2137971bea207bdb91acb9be1bf33aaac12c4db06939596e029b04398282cf4 +size 7106 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..34604fb026d0abcb664c38e460711a7b33bc54ca Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_210699c2baa09235e112+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2d97ebfc93bd3ce3b26648c316a0ddb9ebae2f70 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/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 ' -O1 --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_2f253907beefd0240403+793f1a96/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..89cdbad77bd929cd20a67a65b9c0ecc9bc44b2c7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606694f40496858e48b042dadaf2b67060c2a2f5cc13983ebfaaeda38a7db4de +size 47194 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..550ff5328646eebf7080b6946019d1abcad9bb2f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2f253907beefd0240403+793f1a96/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd661e28ecdfaf1c4b1362d7e3080d5f2dbd12f26b1036af5435f53209c8c7aa +size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..54652711b881ed95d11360a0397e86833329856b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/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 ' -O1 --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_3f0b0e6212dc79723cc3+7e4da68b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..44e2b3dbeb4446bbe262d6061a846c969ee78d0b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e578af1e7a1de600b45032936e48542b291fdc730887158100826d41680c93 +size 45872 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f1a15282632c7f43ee46075877f863ecc6c1b7b5 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae229cf9481028f6d5ad93f458bca08764b5b2f4211672820136cdf785dc308 +size 390144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..83de5e2231e194d082749b744ffe82401fbf1c3f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3f0b0e6212dc79723cc3+7e4da68b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90a1eaede11cf1d7f4c0d27fe54b25cdbc06455fa4a5ac85d414bd134e4c596e +size 397874 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2d97ebfc93bd3ce3b26648c316a0ddb9ebae2f70 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/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 ' -O1 --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_42eff25e6747e007380a+793f1a96/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..704d27e04015af11aeefc3f05d4e9ff7b01033a6 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b58f20429010c51cfffea333665c28bbc50bcfb4cfbfea524337e48abad5a5c +size 447519 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9e6a181f493b170876ca858eef056cdbb03ae97f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_42eff25e6747e007380a+793f1a96/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20f29677c579e42c38a5e0f6c3265139441c8066815c3fdfead7147cf656617d +size 25181184 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..2d97ebfc93bd3ce3b26648c316a0ddb9ebae2f70 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/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 ' -O1 --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_46db6cb5e1cdb009ed38+793f1a96/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..5962bed772570ce908257368e65dc535f00df158 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a3ce75858a025549f5c1a8c5b259f833f7a70298977d8bcb31b69fbd7baa354 +size 482022 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..13945bd874cbbdf8aa6f3ce6fe3067ee67e518b2 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_46db6cb5e1cdb009ed38+793f1a96/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:275604dda3dedb594131871606492a90bf02c0cd403cd9a4191db0cce836e60d +size 6421504 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+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_493e78641761e8b5a857+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..477830e5869c6dc8f89b1c7ed318cc2a3d6aa809 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1126587d06c2dc5e88990726c9b5b49818ae491f81449e4ec1713e53b7cfee45 +size 7099 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..53fb78b5efc55b3048c2a8bb3906bcc70b96a691 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_493e78641761e8b5a857+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+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_4b14ab6f395240df8643+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bdd2e2a0064c634263785913da590c5b76d79a3e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd99ced4ce85b798eb3906f3c537fa8aa0db903aa246441fe303bab63840ed0 +size 69058 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..1db20fcb4ad4694e71d573fbbc87c7a50b8fdbc4 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4b14ab6f395240df8643+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e15e1c999a6c34eddeae1d2ddff471bd8274c161b0cdf9f10a2397d0a428ff6 +size 1158144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..54652711b881ed95d11360a0397e86833329856b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/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 ' -O1 --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_72a72f9ba9aecebc0ec7+7e4da68b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..551e914156114d254b119588aa04c05f635fa528 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b24ddd83bc533bb0dc6fa01f666b270f6b56c456add04c37bc1e13d125e841ea +size 417838 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b7abfca8f6836379676e9c882b87e6e865206888 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83ca8a3d3686d76ee3c29ae6cf65f74f5696181b9989f5e1ab91d989132e40f1 +size 4312064 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..59d56d0398f06d4ef9ea54a1a1428854d51d83b7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_72a72f9ba9aecebc0ec7+7e4da68b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488edd1540dcb498bdb7a9b1d0a3073fd2ef38106f02011bce80d93e89f6869e +size 4381935 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+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_8843c20ed56d595d2236+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..d7edf89fbbf263f55698baae67012e9bae86329a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e60ea05887da185382584017c8ab3cb1546ae53cf6e60d0c9397754b7ff724b +size 7113 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..118fee5ccaedc272bc032cd77e13e023c1efac9c Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_8843c20ed56d595d2236+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+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_9781cf9209feafdf03db+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..dcd1f5ce5fa97a4657f72387c6d00069ee60488f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d1a0a75f98a7c028617eddb01556fa74f5a8fc02d45fea6183d4ec9040a2c9 +size 69051 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..295096b21d1d9afc12750f5b2d45574e27f686d3 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9781cf9209feafdf03db+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39d6cdd765b0a5f8070ec281783972c5132e8aeb5dbf37ff5d70e9719afb9511 +size 1158144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..54652711b881ed95d11360a0397e86833329856b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/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 ' -O1 --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_ac566d62cdaa098c3285+7e4da68b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..00c84661d2295f2d35d07074551254e567b841d1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87d1e88cc8264cd8e6174e2301fa2ee0ea8af7faaefc7970bdd517af22d7639d +size 87671 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..095c97de7f54b14299daa4fa15699dcc4ff31a92 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d4c76575a89c7f719ba050d61906543ea5b994b42383a890c674b9fe0d0aeda +size 2325504 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..c51825e00749d378b5f922ffae6166e80c3acf5e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ac566d62cdaa098c3285+7e4da68b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb72ed753add5d51f166812992c3825f2ed84bf5b6cfa60fe0bbe9eec97a0de3 +size 2333403 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..54652711b881ed95d11360a0397e86833329856b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/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 ' -O1 --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_b9b3451de340b8eee93e+7e4da68b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..82f40b7992684a38ecf52a2bd012e4af3f177142 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28bbd441aaf14edb23f4623a1c9b5f6bdc6509852df1544dde2dbe00decaae6e +size 412964 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3198104c978bf8c138af2f529f31e2ff94fe06c9 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fc0b66c9782944b7a36e7feb7fcd2df82daab6e7a3965afeddb13c614075385 +size 2212864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..943c582afbf44efcd8aa404d9d0085f0266b461e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_b9b3451de340b8eee93e+7e4da68b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:607f2fe98ed224b90067d330ce364e6b6f2a8247cf016cee7b72344c9784aa6d +size 2282608 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..54652711b881ed95d11360a0397e86833329856b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/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 ' -O1 --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_c897718453cb0b8597c2+7e4da68b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..11e4b0533b82aa7991f0d6429dfadcde71c3145b --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14e6e65cd1f7c168ba29ff3028d8daaa7722ef33e073fb68b1507831367992eb +size 50060 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..ba3722c5881d9753e570c69ca36e9b6fe2c3fe7f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5195d6a0f4fced9a4bc8cc05d2f3ed94e74d1c88c551aab473551a8d63cd20c +size 2356224 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..9889d7fb2a11925acab5e3b5dddf4a661b51942d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c897718453cb0b8597c2+7e4da68b/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a875e627978b9df23c1df56daef5a216a10baa81087514c494ee1e28f067c0fd +size 2364014