diff --git a/.gitattributes b/.gitattributes index 97a194ad0f5cfe1602bd0476b838c7d35d89d45a..fa4bd75efd645d7afcd5b881127232e9b6c13b02 100644 --- a/.gitattributes +++ b/.gitattributes @@ -3571,3 +3571,12 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/model.neff f neuronxcc-2.19.8089.0+8ab9f450/MODULE_9d6472a07252b0ce1b30+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/model.neff filter=lfs diff=lfs merge=lfs -text neuronxcc-2.19.8089.0+8ab9f450/MODULE_9df5787b5ac6aa6f2003+a9d440f5/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/wrapped_neff.hlo filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/b851469c36fca337cb63.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/b851469c36fca337cb63.json new file mode 100644 index 0000000000000000000000000000000000000000..03ed84d18fd74383e85cecd9e834878b7b8991f8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/llama/llamafactory/tiny-random-Llama-3/b851469c36fca337cb63.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": true, + "optimum_neuron_version": "0.3.0.dev4", + "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/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/b451984f224fe0f3ba20.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/b451984f224fe0f3ba20.json new file mode 100644 index 0000000000000000000000000000000000000000..6ca461006d711546b098c1012e18e853fdbc06a0 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/b451984f224fe0f3ba20.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.dev4", + "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/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/cc411d7a2728d29949b1.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/cc411d7a2728d29949b1.json new file mode 100644 index 0000000000000000000000000000000000000000..9f4b9f710568bf9c663446d9dae29f5a24771cc5 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev4/qwen2/Qwen/Qwen2.5-0.5B/cc411d7a2728d29949b1.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": 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": "0.3.0.dev4", + "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": 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_01af6db1929577719d82+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.hlo_module.pb index 6b9a9d6872e73a30d8926a346b9dcbed7cf2c014..25cb4dc1830f516f149ac2495bcabcdfef3e6b3e 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:bc7e7185210f12f6a2eb02ea192cca41c851d62bef86ae4edd72fa5c1658a398 +oid sha256:ded2249dce62acb4342c71d4845a9b35d614bc879f96bb51b59ac7ef116de083 size 52490 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.neff index 1b1ef469cd74940567c25073299bf7f657e12ae6..8aa322ca98bd28f5e3cb636d7a435911ba0a808a 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3df70213923e9aad11f04521bcb75900cf7041d3fbab614a66a11045c652707d +oid sha256:8fcc7e4611905ceb085a5044d5d67da7672e63f17b106d1449d74faa15833ff0 size 185344 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/wrapped_neff.hlo index f5a020e7e7f8684af093e659511b14179f879dcc..1ad367b7d4d43c581a2a077ec53d378d2827ab72 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_01af6db1929577719d82+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:83da799e58f62ac78702dcb279044d009f4bfea7bbab3d13204d8f89027ca834 +oid sha256:1bdfa94a6edc83f03954bec307333ccae2afbd91e744fdd799dd7dbcf8d3bdf8 size 195507 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.hlo_module.pb index 1b5464b54191da5ab8543d3bc7d77e592fc4f5c2..fc15026b528799df31d5a1e35901ce55b6720296 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c7247332e2a30e23667bcf96312db2825f0dff9a5edd81bea17bcf5e84a200a4 +oid sha256:f56f78b3c986abcbbb3ae075a5f2302e28dba79156f23719feceafc0419b3986 size 81342 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.neff index 8613519f8a2afae39bc372f702ffeb5636bf2e74..40a98cba4d2844fa40a24ea59cf249cd696b29e3 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3e9a55404a52572809ba5ea4756e4e9e2b648d9f971e6c366defad000bfe8511 +oid sha256:02f47938ce74cafed0379c011af8988bac4c7900709b2e317e41ca27ebae42da size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/wrapped_neff.hlo index 8e61339e97670ea59af0149013abf7beee01db1a..9f627e4a31ba137ad7b34290c9d8c6573dfeea79 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_03d38e403ebd62bfc408+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e5f68c9acb488bf85677917464c641c5623dca68d9f1c798dc5537ac2e951540 +oid sha256:46924898a1be77320b737213fac787a3e8fbfb09a18da68ee658c15a2fb8a075 size 244319 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff index 5099eaacb8dac91480967418d9b4e17f6f0a3b6f..d026f394f067e7510b0f4ac7a27fe2cc8be2abe0 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_0507b0705d8d1fea9bf2+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff index 48881abc5e763b6a3441051ca642b04ca0deb9a6..f92dbedefbd80d11290371c0da2d23187fdd9572 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_0a941a976d4537ebcabd+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff index 4f08a8cb2df5054f7605f3262a1a04aa2e635652..908b5a3a7e7fc063fae1c1e255ae559d9a61ca39 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_1c13182ad393459c74b0+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.hlo_module.pb index dccf38952d680cb11b432c4e42a3a2db917004bc..ae89d81ae6c44f33a58182e4491a266210bb5777 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:18326d5fb6180fc809a5dfa2ec9bbde3caacf1caa0263ecdcb34b77e5b13e7c7 +oid sha256:5ac6cdda1eadecd195ecca6c4d9af6883e0ae0c8f779dedf4ea860d7646359a1 size 79534 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.neff index 67f65cd8b66daff09b60733d58ef778f21811cf8..87b64dd3a82cafb0c2308ff01bea47d4c5a48614 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8c00586c7331ea06da3376b2c5b88c9ba30533b6fb8731955c589b37a9164758 +oid sha256:bd31746ed43c76de3a02592868cc53552bec3006fbabac36eb6f3d6f6504c3c4 size 216064 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/wrapped_neff.hlo index b21b1c6fd559cda9467039223007b22577bfe289..cbb5806b0a4cbc06cf2388907b4963b1aa788672 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2031502066f33605d0ea+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c85fb0e6853d63b01037a7f56e7693f357d47b0b61cfea76bae11557e43d3f54 +oid sha256:ddb7a3c2b19ce82ac135f580e31b96d1925da1777cacb610b176583f3e9aa607 size 223770 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+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_220660811b31ee5ead36+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a12c885fb547cf2668dca58a76ecf02135eef1fc --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e2d997c17bac2017d5043a78f8d08c9b2ba3ccdafd20280ea49c9f33d694cd5 +size 81540 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fb801ef7019f031af0cfa4570dba2717d89b7659 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92331e32d419d418e6eef5ad59dafbf2ce56f01b5cf1e29ef4def72f5e3db37e +size 461824 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..5775340455d0c716790f07688af00e68d2444e86 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_220660811b31ee5ead36+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22e24a6e3362ae8db167e74e247bcd7c095785d8b5f998279da74a7b84500e6d +size 469663 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.hlo_module.pb index aad98e50817363a5a27104af12ebf769ea14f91b..a6af7d0f6372571c74fa144527c7d0e010183b0c 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:a4190870df7e587c49fbeb3aa4eb5996292c91ca7cb812297c3d52df0f9e3675 +oid sha256:48d570de437bee27addca79567e3f95bc342a186a40d0bc067cfb000ed5f0ea4 size 89230 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.neff index 6c9b5c71eeb4438f07e93dccc9959e7bf9295d36..ce032e04d2e9173c91f7a1806d92b0a3a40ed77b 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3be6ef9cb6d9f18cf8d09ef9306aef0bd1977685275d5a18dc823411b74bae2a +oid sha256:9f74a711966837a1e383e92cdb3866925a8233dabd2e0168536fe14215d92fb0 size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/wrapped_neff.hlo index 4df8eabcad383486061a675817e12e772a737fd6..7a9897f00912fd5b931477f74deed6ed55d6f097 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2a4c6c07772e176d6bff+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:44ee4ed8736267c9d576c3570ae301231b4b4d78b17d5f2ed88b40fa9300764d +oid sha256:64fc0daf96791c594fb34f68afeaeda8a25af72e3f49586c18c823506102faad size 247153 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.hlo_module.pb index 311d4c0294f2bb8c99f89f4a4ba20b903669c442..1d1f8e37c78ad9b041837cbc24275e6360123792 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7a246bea7a7b699f74516fd8df7a3ef93b9cb13b04c33860e496161f4ff8e53d +oid sha256:4cf231e78d797aeaaa85a9adcd3061fe1a5c80d41e33827406344b7d993a3423 size 47085 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.neff index c1778b43e32a18bb4613276f01cfcd0f0e88a195..986f60422387f33a9da476bc9b4784f0ee6ad380 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:740142233ab5e4d2667725beb273f35c21a2b90efec957b376cc07650312a00d +oid sha256:ea2c98b55b32183253a40dd36f7a1ffbdee46446ffe5e34d0fad688a46bb33d1 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/wrapped_neff.hlo index 4337962a7df8a8a3a3b9cab28d300fbe1866bc9b..30ae3dfcafa3111b2c7ad1072c10e9bb3ed4a90f 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2bf3848e1bc7d11bcf27+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:883956d16990891b8849db61efef36bde4b7c82ef4611e406fd685f61d2f9592 +oid sha256:83b68ec6506252488f8e7b695eddb67f0be404486a69e47f27f192ec08eb29ff size 152045 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff index 65a597ae64a8b8743728529dcef52080816b9a99..854cd600e36d0cbf33dbc4453d1ea30662aed8d4 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_31e14bab9c1ace8902de+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.hlo_module.pb index 74dfc224aab8dfbc56708bf7efc4672fa6be3ab5..c3df99c0fa289cbc310f4af6c11bf51473d54c9f 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f90785b02824797ea0ae29760d7ce36695ac71f4da76c7cb6589fb60a90c57b6 +oid sha256:e5d17778bee19e679b21f8df23dcf0f686f5f5fde465ee27c15a4af3ae283700 size 79534 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.neff index f1c295a90b29feb58d2432010c08be5287cbbfff..0cbd7f0cc6410e7cd7a40ae7b49d14623888d3ae 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:129e28e61e50f1c96f703481094ba4129093724f04ee4941f0acabab64ebc643 +oid sha256:d052436ad985e98350d77b633476e9d31be12c8b67be9ac9c3d7bd8279109d9e size 216064 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/wrapped_neff.hlo index 15d362b11f93c261c213b6132b07d3f12642209b..ae72c73eb0de91dbc1ae04e2156837ef78f488b7 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3ae74890eb9055522dfc+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4946e6a857af4ea5708290e96abd80ace538f381924d26a04c26b766de975387 +oid sha256:8e52ed63dab973aaf0e89d040d580c2affaf2aadd73626a6a261271c450451ca size 223770 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.hlo_module.pb index e368bf4cf425ac301b040efb612461e0a4c42370..ad593335cc1fc35a08a45e49e7a5f46bcf46b588 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:34b8863e5e31ca539aec62a5330c04e1f4f7761bf994412bd4f1825d4773e28d +oid sha256:146feab8982c942ad32a864ef4d88695887e1681a5d618f18a99a0a1708d4fd3 size 68831 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.neff index 40f8b501def46650ccba342b0b5851c71657d641..2aa59e9a5e5cfd9a87528c85e2f6730816ed80fa 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c15c052e9c900cb4d557acfd90d1cbccabcb7d72d3a5269f3ca131f475a08b5d +oid sha256:3e076bef02ff9d09365b69af770dd7dc5f58043842933e2e976950adb9e10520 size 257024 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/wrapped_neff.hlo index 29e2fc686c9e0bf15352875593d5b949648fba74..ec43c368ec195378aed9a33a1491cdfc637596cd 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4ac4f5ffa7821caa2254+63ea7cf2/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:76d1eb8404998b4bbd242185690a39d1eb086638690e04b96366db5e7b41bdc8 +oid sha256:8fb4a3079307d33ea3f574db4d2d33a5f09bc40f08f5434fdbe857a0ddddfc6a size 268322 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+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_5627f723c34915552f53+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e1d2046c4ff2fa7c056147a379c1613ef8870c42 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3f62885052a881aa88a96bfb03f808af3c2e6fb11ff20b71411aad180cd5c7f +size 687486 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..26960990c0edd4d8d82fd1e65b632f88372fa967 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5627f723c34915552f53+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:094a9e95b4e8218f9ac4e12b3176aa08ee8b9d6a01f7498db8b26175d28c7797 +size 19487744 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..dcde6c3978ed8b79ae83ebd29a4874956f871e22 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+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_5ae48eb0cb896a33dbe4+bfe5714b/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..88aae00e4c1c6abcc5d7bdf6dddc5aeb38643b52 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba0f369eb0bcb64aa67cb117612f2281e3dcde73bcde7d96fb7dc52b7982ec0 +size 91298 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..3d87c8e26cfbf842e912f871c368d2ab57b499bd --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5ae48eb0cb896a33dbe4+bfe5714b/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a2f3511db4181fcaeb3a69b114dd657c77c3f65393ac50196ed77dc45937d94 +size 213842944 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5c7cdf7c9d803720623f+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_5c7cdf7c9d803720623f+431f5505/model.neff index af6129f4a675ceb42bd8d0e11d2bab15431038fa..d1ba843ad1e827b35dea47e826c1a6325e72a8dc 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_5c7cdf7c9d803720623f+431f5505/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5c7cdf7c9d803720623f+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ce0e919044931f1c6ce8f82aaafc8ac84d23f1351c2ccc221f929723cbb04437 +oid sha256:999f5c5e325eb369b07ce8abcbad1703a953548b28c30e15fbf47b4a6bd9478b size 103424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.hlo_module.pb index b81e3ff6c3f878d00fe35b74b53fb8e3f98ab09f..112c6383790ee1d8532323b94625229b9f784e67 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:32329dbcfe40d77d5b7fab482041cbbc6d84800ceed3a20a19261f5e3ddd36a7 +oid sha256:bdfeeb5401951679a6e81aab655275f13a93cdc7c81b78b897b3f032529f7dce size 81342 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.neff index 90221b6a3c4efcf749c29fcab6732952e354cf5f..5bfb6703c5a755ad395926f729ad784d549b1568 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:88a629f47632431528581d85facd7912458f11cf897aa8be6a0fa8d39a1f0076 +oid sha256:211509fb27b7dc5340ecebb4dbc9c8dd8f3b4065fd89d120fbd1f878a12f7169 size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/wrapped_neff.hlo index f7b8e3167987ca024e12dca47dbef8b05ea772de..7e7d828802f5ff977a500cc90dd770e7f3eea732 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_5f49a1d8795d09fc1c7c+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:72a94cf38fd5003389afb8aecd8f850f855043d511e4f2e4e637f9831094622e +oid sha256:6da46b789ea4310b288c33f09c460aea9391e30a3c84ebd08483b4f7aaa1ce0e size 244319 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+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_64149c86e6e1f50fef79+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..6a4cb0adbd748a6986666b284996fcf48a3538e7 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8accf4a8e05ca6c46132e9f38bea7e7a3c419937a39ac087f4c2cc195bddbb1b +size 619941 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..c5e40e7122cc6f5b22b5bd8e7ca16605c0631d7e --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c137346df7c096cc2a1e11ae5134c442c3a274865ffce05b77dd8efd11f7245c +size 1117184 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..ef7bf2356dc29871d3cafd96aaa5c9f050eb8dc8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64149c86e6e1f50fef79+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:784b9b378c592cb8537f3bab70d303829252fcb59fb70a1e8d0dbd7642218bf1 +size 1262210 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb index a1d50bd07ba3098a2788d83b1d6d78a5882a5bce..c697f34024577a70f19b3f613b959baf2435c403 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e8d6077de8d68a05606afd001979d23e8d54fde393715044dfa207b8a7db108a +oid sha256:950c7ae8f6488236ba4ba9bb08a73a6abd406e10b7822f31930a4bc904fe3049 size 82456 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff index ba9770b5e8bb3995b3b16f4aa8b38e1c60c43650..cefe618e1a8196833a9d80fca626e3b87a45722e 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_64950c85776a119cdf83+b001bea4/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b05cbdc120dd257d8394be5bcd037f5e0145c6461b880c38dc45ecd80e48c0b9 +oid sha256:3faaa0cdb1a48cf239e81ca0b4e1ff9a3b86579501182b940aedec66041c772b size 420864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6a7765cdd7439b14659e+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_6a7765cdd7439b14659e+431f5505/model.neff index 5a30404089bc81156d441db3687cfa871a6b8b21..0244b7e1cf09258c917c85e4ab671153b515879f 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_6a7765cdd7439b14659e+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_6a7765cdd7439b14659e+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.hlo_module.pb index 6e1aa1457c64d5641e5fb81d815d626fdc0fc6db..3364f44a9d058fdd7f1723919e56479757b3e96a 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f811eb3e09d070497eae108e123e12bfbdf3bc63b33f9b74bc1824912a0ac97d +oid sha256:9252cda7ca4a7749dfbebeba224636407461e55aedefe71421425d2d9ffbc443 size 68829 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.neff index 5e591857468b013f36482dacb78e27158f6c3141..9d0511f89bb3c0faf96ae5254b9756475690c2f1 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7053799d3bfa4f21a34e73c218119c246b59f33e8ca963466797249d72ebf254 +oid sha256:14081373e76a86187237e7b02de156037be1b7e2adbadfccceafc0957fbfbb4c size 257024 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/wrapped_neff.hlo index 34b06e9b6b5cc138d2b5c61c544637ac94555471..6d196e0cf8e12284c1fe6575a30f29788e45c405 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7af77f8c231b0912b481+63ea7cf2/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0c97e3b684db71d95d3b1127ec173cc6081c8468350ca58e371150fb98c89dd5 +oid sha256:d4f7abc5881cae7b3dd80ec0d9e3c9e4bb015044631c25a92f68aa2008500098 size 268322 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_7f00c58343c6e5a64667+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_7f00c58343c6e5a64667+431f5505/model.neff index 087bf26d06995f2d1fe04d9ed8800e3b71cc1fc4..742592a47c4d7404cd9ef14bee9381b361af4df9 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_7f00c58343c6e5a64667+431f5505/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_7f00c58343c6e5a64667+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:c112f959e78a12f7ad5c10f6778c8cb6a6e20e6493052f238980f4dbdaf93792 +oid sha256:f07adae1094c2c32e6ebd05cfa3ffeb0737998906887cbbafe99e6b56a7b54a3 size 103424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.hlo_module.pb index 20c5cc854ba85c757bd20741cbf1dd1e94767786..893b8b232b819b3f4a9db3275d8c76d8359fdf7e 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:38ee2f66a15826d8d02affbc64590ffd6f4849aa667d606e46ce0f282f098ce0 +oid sha256:e689c2e68d2c93090901a894226be49c23f19dbbf477299cf9f4bd755fc34761 size 79983 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.neff index ff20d932ea67efa7bf881b807098bab77ad35957..0cba5f0826c2ea7a9a793509deea4376fa607bbb 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:046908eb512c826c06f5beaae614cb191b19296af7accc9ed99e4a794afa8168 +oid sha256:3db84374c4b57cbb8609208cd5e135ef8892132ca91bd8dece84aaa614683f29 size 318464 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/wrapped_neff.hlo index 1e22fde805afaf8a7b28dc55ec356a6847dcf4c1..d013012211c91a4b0a4bb05484447b8603f81182 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_8c2a6b120271c37fee40+63ea7cf2/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1a70f48ca0ef9cda5294f463f52de110526695a8e90ccfca9ac429a06b960350 +oid sha256:89040990e1f22ddfed1d9fd55d1af587ab82750b80ee764b3898592094943f3a size 329762 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb index 5db319518dee8749e2f1e99c9505e5d18e460dae..136f15a8429cac114aab7561f7106db8b06e1387 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:dabd7004df6faa46a5bed2da843e6077fd70fd64a670e9988cf4ab4f36dcd912 +oid sha256:9e9f41fa5c9b9374c01e392d69b6c3d7f36f1368531db9d6751cc1ba7a5ec046 size 81609 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff index 9e7b038e37ef393a0787da208abbf3b29348670d..679121f8b2cd01904befc5c55ede298b38195d1b 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_92d7a6b8bc621dee02b9+b001bea4/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:418340ed0f5daec6397af055e4e237c35cd38b71aa9647f5c35b696e9b4c282a +oid sha256:ce30ffabe94bb1b832498ac32a2fa55536c0c8ee4b9f974fb3fd3a3bf121b2de size 359424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.hlo_module.pb index 7c7f54109c7b2dfa47108793669ffed33ba64c25..3ec499a1de124d05d23c44ede6ecd14bb411f509 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:aca923d5616b066cbb9b10fe6c32d0f300936671cfcf5ec1ab89e4ba297e5781 +oid sha256:d7f73f81861e91f07780716d0f141e95d1b0ea4f5311f6eff20c3ce06b0838e9 size 44602 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.neff index 71b37e7501c9ddf50188c66f3c21d118ec2008fc..ec251d70c8c29e473ce2002a7e40d2af328c37b0 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3d74269d679ec8d60d8589a5952473e895bcef8b694f516c97a7c4c54595eba2 +oid sha256:169e783cc09cdc0d1b0823fd7a111ecc9fbf49f924a9be17f51a878e92aba489 size 175104 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/wrapped_neff.hlo index 5848b9359409abeae49bcf869af5220430cc1257..7a2c7ffcfbbc42f41ae6e2901c4bac0459feb8d7 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_93486ad8f65a66501276+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:087ee3678b8c7d2ef629708e7a218aa504fa2cbb3d73eb3446e6150026824f25 +oid sha256:2bd855077fc18614f17494679dc053b1dbad78565a0e48a978cf6ae367ae90eb size 182770 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb index 48cade0b6f59e358563ea3e04ad7bea97a1522ed..17dd923713c55bc22b142ce7d0a652787b155500 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:daa935dc2aef177aca71aa4c0b97090eb5971f55c8a833833000e9e9344bb9cf +oid sha256:ab5e18e9410efecb6810c338e154e10a514450771cff5afb0979bffa390238d9 size 81607 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff index a9c82691382ac2049e189b1663fb1a8d0b186c8b..e3cbb87d419e5360d461e33f13d909897a2064ce 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9a53db93d18e769ee7ea+b001bea4/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e15dadfe460e410ad71cde19020dd05dedf0f6af671a562060ea3e18650ecb52 +oid sha256:b2ddd0f88ac73e064a470bd0f2f6100b05f7f9d87229ad60107c9303ee52602a size 359424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.hlo_module.pb index 7abf4013e6f6a15ab63aee3d80883afd8c358612..3c3ce01d29b8184ffecc3b191c0da69f7e5417eb 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cd16add865b12ae3806c07a1213c995ea0099b2d14689ff1eb558d1ba1dc3e7d +oid sha256:c92ea3bcb8c44bca3d18c7ba1528a3755e79fe86d148d9736557d041a619820e size 83825 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.neff index 413f41097d6451a9fba0980d8efa1e47ab5079b7..b6d33e89aa2cb599e9d302d23620adffa9f627f5 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:3a6d0f702f74844edde92a820ad11a89f2839544280dd5ce86f81a653a326c02 +oid sha256:7934fee2135311b6f418d6acb4750cfc62deaa2335df12de260b17817049fb7e size 185344 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/wrapped_neff.hlo index 7a7c88baaf363b10607c26adf48731657b2b1a2f..f78abed414ba15891f186f0831a7627cecb863cc 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_9ba097d82cae64a421d8+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0cb97a9a71329183f2950e71118cea5c89bfa5da7453fb14ef74a5bbe44da0d8 +oid sha256:6d80f82a8a209f0e6a22fa47e2b62c396574cd48f6bbf9b7b26620a7ea79cefe size 193114 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+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_a140491c564e6bf195f8+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..938e7f7530bac90575b0bdef113700cf4934658a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e819dc05ecabfb98da77c8dfc10e04c1de711b67ec608d686399606542c95dd +size 149919 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..a2077ff6fca91775aedaec3af2184707d4de632a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_a140491c564e6bf195f8+431f5505/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da98d189f2bd84910a0d7f0f2164846f11992fb474e0f2187705c9019e4a5615 +size 594944 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_b7aa701991786c2dfc6e+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_b7aa701991786c2dfc6e+431f5505/model.neff index 9eb2c59dbfb22aca263f8c50b88d8592cee5e4f1..6fff5e33df1c20da980cf33f47bc027d9b4fe16e 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_b7aa701991786c2dfc6e+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_b7aa701991786c2dfc6e+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff index 95618627e06b3550ca4e40b034307491a2a3e9d2..9b87e28d752c345547ac6946ef891dda0b783f2f 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_c6dd950c4bf878ea25a4+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.hlo_module.pb index 52f6974122eaedf426538b9a8c696d2c2cb4317c..df962ac53612439198ebb25188739f2cfecc0ebc 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e8d5f38eed070917832ee4e46d54e9d3241285fafa27c20907e573dd208e12b9 +oid sha256:3c8aaf3a910a58c8365b60f7a4eef43fb615dca4f5ac573ae1d2709f761dc414 size 89230 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.neff index d1fe5bd3f5eb804824e92f15c9cd7449376394a1..020eb05dab2036da519ca784029679ed0bc77e6a 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f29551e52e446e1afc543b715aecdacc1f7c4bc4c1cc6080db60f428eebc9ef6 +oid sha256:1ff91d74f953457c77c307e3448478f7d76c75db5ad0ba43498fd624342e61f7 size 236544 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/wrapped_neff.hlo index 095031b62329a5ddfc1d35b826ab113c6f5352ca..be3e839108a17eba7ebbe01ae5cc4ab369b3336f 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c71097e8f6025fec59a4+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:f64f08f3f1d896ecd31daf8c9dbe190cc277e9d535e831ddffb782ae3b56482a +oid sha256:f51eb55dae750aaaca63a26a9b3e6d82fb01cad470e9da22f12ab5aba7d4220e size 247153 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..9932c70d27d759d781be88485b74b17b49b4c04f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+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_d1836f52babbb77eb196+431f5505/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2a3364fe8c50922a5dcc01311d1026495eee5395 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:312d395e21c3a3906ca3793fb3eb4b7969c0bcf440acdeb74a6ef6ccaa42d054 +size 7106 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..92d82ab06237d140fbca9a594fe0e3a37792a346 Binary files /dev/null and b/neuronxcc-2.17.194.0+d312836f/MODULE_d1836f52babbb77eb196+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_dc0cbedebd6955513631+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_dc0cbedebd6955513631+431f5505/model.neff index b88095dc997bbdad3d8e278b89500366fa4b9aa0..e48782f49e5e78e50984f08a3344f47c1e42cd2e 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_dc0cbedebd6955513631+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_dc0cbedebd6955513631+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..e1dd82452b8e16fe8d25db04b67b50fefc4d0215 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+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_df1c38ce4fa219995eb3+165e9558/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2c034d9254023958f7b7872a76d7da5a4aadd11a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a123415f879e68753de2bc34f6b789b77fbe4cab4a75895c5df494ce537378c +size 619941 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..fcc0cbfedfcd2011921840a952e2e85f40b9bb68 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8940017a5be0f388023ee129003fbd9b5315a6a9ede7de0ca1f10ccf59008a +size 1219584 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/wrapped_neff.hlo new file mode 100644 index 0000000000000000000000000000000000000000..7754d1c1e0782fb2ca7cca6a60426d2d2cbe53d9 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_df1c38ce4fa219995eb3+165e9558/wrapped_neff.hlo @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9a9dfcd1303ae250e2a89c75700cb5c27dcea149c6d61cef7d5ec9bd4102902 +size 1364610 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e30bf980b957282a9728+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e30bf980b957282a9728+431f5505/model.neff index 5192db03c51225c764d2d3a102e2d2900973dcf1..c0895af29f622429d6c6b733f881e097d60f3428 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_e30bf980b957282a9728+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_e30bf980b957282a9728+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff index f20637fc6797213610dc9607a0f981d3bc07930a..7d828a61c9cd1e5521a58a3c1ec5b6bca1371ef9 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_e3a13b85dcb5dcea901d+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.hlo_module.pb index 2d4ebe2adeb1c2fe4d49daa513484296d0e0ed41..a4f5227460e9e79a93d8003bbfad088389abdcc2 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:4c6e9e4524b83ad9d134cb0bf2a4f3ec0adde39b50051e5d885478d8dac62e5b +oid sha256:473c8e9b1bb73f57143753929fee0a9c3915925f1bb5ae35d6a3f9845843973d size 42794 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.neff index 7515ff8280ed5d93a8ae5b9396d6059b9b5a6184..e07d942dc0e3254a0c879a6f1613713eced9d2f3 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0f665328628f7abdae2fe10466061620c2ad60b349872110003e39acfa069747 +oid sha256:df1abb5b986186651173b1cbe092e14e6e59c71d212426cf427a25123204e0a6 size 164864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/wrapped_neff.hlo index d2bdf0a4f6dbffe2167ae5d534e8a5f78ea7097a..09a8a14190aa479b2b3c77680f6cfe646e593854 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_ee8cb7dd9350a372ca5e+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7c327b67384de8ed1c70ed4a1364fe156416700790423ac6dae32da84c6f7147 +oid sha256:0817c56041ebcbf2e33ec5b0cf6fb9e24752b33e2d6bcc9d72cf53bf47cf28fa size 172461 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f3190a8210cd76cb727d+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_f3190a8210cd76cb727d+431f5505/model.neff index 6e9f4faf5da637e29bc45bbe5c870a4e58591b94..c19e3db8092290b633ac43ac63532293a3b965b7 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_f3190a8210cd76cb727d+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_f3190a8210cd76cb727d+431f5505/model.neff differ diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f43684c4be211c439d1f+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_f43684c4be211c439d1f+431f5505/model.neff index aa1d5611bd6d6666077b95e5002851da360f9135..ded5764ee5b668f85f17dc8e5fc3711f79e752f2 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_f43684c4be211c439d1f+431f5505/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f43684c4be211c439d1f+431f5505/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2587a700449736f623b9d9a187221781bd442e24517cf5833fdb7f3d6d6dce62 +oid sha256:eb49807f5b0027557d806e79dd2fd13211f0456ae73b7b8654221bf4a72e1064 size 103424 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.hlo_module.pb index 1765dd747b659e06daf3fc7a91a53d910ef1b8f9..dd2921b243b96c868b536fe4fa66aa6f95cfb674 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.hlo_module.pb +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.hlo_module.pb @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d3d5b0b11f69a6896ea95e9f02724ed80b1a7dd219005d4d91cf35c7e0447e82 +oid sha256:de1b150862cd532b20d4868922c70efc1dc1af43a0a660e13d7c3e2eea501b20 size 83825 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.neff index b5ca0e25720721df66ab722c8107b16d8762a10e..9a8c54908de3fdb89d04fb521d07ad12c747c85a 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:2fe84f10f8e975d6700f163125c25ff096ba2eb5ed88afee0c059a5023c06fec +oid sha256:0eaf2aa244102b2a3b5ffd3b814be0d6b3f70eddc95f9c86173dfb0d73b6cc10 size 185344 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/wrapped_neff.hlo b/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/wrapped_neff.hlo index 6eaeeb3d1b39724a90a98d8ba74c1733c041b21e..df64b79e599e66bacba028cb261a757be951c769 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/wrapped_neff.hlo +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_f9fc90d7b6679b6ca84c+165e9558/wrapped_neff.hlo @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e591c21506e454a928bdae8b80463737c86ec3b6f1a766a384cc63d1d28aaf79 +oid sha256:6971a969540d83fead56356497ab37c6759d18ffcdd093f34972048b67a27b58 size 193114 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff index c7c8a9be0c4f509560de6d5279e384b225e37b6f..bf653059fcc5e3bc6d885b19808d1f357b725140 100644 Binary files a/neuronxcc-2.17.194.0+d312836f/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff and b/neuronxcc-2.17.194.0+d312836f/MODULE_fbaa5b03f774dfaa214b+431f5505/model.neff differ