diff --git a/.gitattributes b/.gitattributes index 710b393c48b0b8536ce612817e078eda3b7998ea..33bfb754c5071e7843561e96e98eee3a682689e7 100644 --- a/.gitattributes +++ b/.gitattributes @@ -2237,3 +2237,15 @@ neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/unet/model.neuron filt neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text neuronxcc-2.16.372.0+4a9b2326/MODULE_d6a9bb00aa7189af3ffb/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text neuronxcc-2.16.372.0+4a9b2326/MODULE_fd6170cedb4fe53c8433+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff filter=lfs diff=lfs merge=lfs -text +neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff filter=lfs diff=lfs merge=lfs -text diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/28037758016041af399a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/28037758016041af399a.json new file mode 100644 index 0000000000000000000000000000000000000000..dabea15daa86bff26dc1e5b9f95f911f914bf6e8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/28037758016041af399a.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 2, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/32ec2689f2e2b8d58073.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/32ec2689f2e2b8d58073.json new file mode 100644 index 0000000000000000000000000000000000000000..fc2494f5718604ccf62093b3cd07a30907cbd6b3 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/32ec2689f2e2b8d58073.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3fdcfb75cf15e31ca9b5.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3fdcfb75cf15e31ca9b5.json new file mode 100644 index 0000000000000000000000000000000000000000..1f3da9bd967bcc79ba44c45c4f42200d7e69ff8f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/granite/hf-internal-testing/tiny-random-GraniteForCausalLM/3fdcfb75cf15e31ca9b5.json @@ -0,0 +1,51 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "_task": "text-generation", + "architectures": [ + "GraniteForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attention_multiplier": 1.0, + "embedding_multiplier": 1.0, + "hidden_act": "silu", + "hidden_size": 32, + "initializer_range": 0.02, + "intermediate_size": 64, + "logits_scaling": 1.0, + "max_position_embeddings": 2048, + "mlp_bias": false, + "model_type": "granite", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp32", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "hf-internal-testing/tiny-random-GraniteForCausalLM", + "checkpoint_revision": "c3074ebc0ac2fe545305f5e5f6cce2cc9b2aa0c5", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "residual_multiplier": 1.0, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 49152 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/610dad84114ec035cc32.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/610dad84114ec035cc32.json new file mode 100644 index 0000000000000000000000000000000000000000..f43f987ab93b3ed6391e086ddbe51c83ee209046 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/610dad84114ec035cc32.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 2, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/b645ea39b56c5af10179.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/b645ea39b56c5af10179.json new file mode 100644 index 0000000000000000000000000000000000000000..2bc87d7df6b53c74fdaefe4f85d8d4252cc94e39 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/b645ea39b56c5af10179.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/b84d42926b5badee9c7a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/b84d42926b5badee9c7a.json new file mode 100644 index 0000000000000000000000000000000000000000..bef6e3f888e72e4761a9d8b2383a05901a648a86 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/llama/llamafactory/tiny-random-Llama-3/b84d42926b5badee9c7a.json @@ -0,0 +1,55 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "llamafactory/tiny-random-Llama-3", + "_task": "text-generation", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "head_dim": 4, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 64, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "BSH", + "attn_output_transposed": false, + "auto_cast_type": "fp32", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "llamafactory/tiny-random-Llama-3", + "checkpoint_revision": "bf2a2e3bf199ad2ee96f02a3c00246c608db22a8", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": null, + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 128256 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/2e3b2c893e5dd12fa28c.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/2e3b2c893e5dd12fa28c.json new file mode 100644 index 0000000000000000000000000000000000000000..b56e1383111ff675b1b776b0153666d5c3b34ae1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/2e3b2c893e5dd12fa28c.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/5f969dd5ec1310f92701.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/5f969dd5ec1310f92701.json new file mode 100644 index 0000000000000000000000000000000000000000..c7d01badbe4b88a86bec61d9e2443c34b9000175 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/5f969dd5ec1310f92701.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp32", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/84c8e75e4defdd9fa414.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/84c8e75e4defdd9fa414.json new file mode 100644 index 0000000000000000000000000000000000000000..b8515a4942d134366e3e2d0893eb3a4978fd4436 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/phi3/yujiepan/phi-4-tiny-random/84c8e75e4defdd9fa414.json @@ -0,0 +1,52 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/phi-4-tiny-random", + "_task": "text-generation", + "architectures": [ + "Phi3ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "auto_map": {}, + "embd_pdrop": 0.0, + "hidden_act": "silu", + "hidden_size": 16, + "initializer_range": 0.02, + "intermediate_size": 32, + "max_position_embeddings": 16384, + "model_type": "phi3", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": false, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 2, + "checkpoint_id": "yujiepan/phi-4-tiny-random", + "checkpoint_revision": "18a9a1168dc97ac6d128f811925670c275610f5a", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": true, + "group_query_attention": "replicated-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 2, + "num_hidden_layers": 2, + "num_key_value_heads": 1, + "original_max_position_embeddings": 16384, + "partial_rotary_factor": 1.0, + "resid_pdrop": 0.0, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 250000, + "sliding_window": null, + "tie_word_embeddings": false, + "use_cache": true, + "vocab_size": 100352 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/2dcbb3f89df1561e38ca.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/2dcbb3f89df1561e38ca.json new file mode 100644 index 0000000000000000000000000000000000000000..cf1a94816f8c040e7c31c96f833b155e70b635b2 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/Qwen/Qwen2.5-0.5B/2dcbb3f89df1561e38ca.json @@ -0,0 +1,49 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "Qwen/Qwen2.5-0.5B", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 896, + "initializer_range": 0.02, + "intermediate_size": 4864, + "max_position_embeddings": 32768, + "max_window_layers": 24, + "model_type": "qwen2", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 4, + "checkpoint_id": "Qwen/Qwen2.5-0.5B", + "checkpoint_revision": "060db6499f32faf8b98477b0a26969ef7d8b9987", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 4096, + "tp_degree": 2 + }, + "num_attention_heads": 14, + "num_hidden_layers": 24, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": null, + "rope_theta": 1000000.0, + "sliding_window": 32768, + "tie_word_embeddings": true, + "use_cache": true, + "use_mrope": false, + "use_sliding_window": false, + "vocab_size": 151936 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/1fd1a2e4204366d503f6.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/1fd1a2e4204366d503f6.json new file mode 100644 index 0000000000000000000000000000000000000000..81538f673557d1bcda94a57358e56c585290fe7d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/1fd1a2e4204366d503f6.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 2, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": true, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/2a5b61ac8a8b5940982a.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/2a5b61ac8a8b5940982a.json new file mode 100644 index 0000000000000000000000000000000000000000..dddef7350c40f329bbbbccc873eba4189679d9b8 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/2a5b61ac8a8b5940982a.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp16", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/b1b72b82166aaabf0a64.json b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/b1b72b82166aaabf0a64.json new file mode 100644 index 0000000000000000000000000000000000000000..c38ef27ee8086c018e2194d79209faf451e0d516 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev3/inference/qwen2/yujiepan/qwen2.5-128k-tiny-random/b1b72b82166aaabf0a64.json @@ -0,0 +1,53 @@ +{ + "_entry_class": "SingleModelCacheEntry", + "_model_id": "yujiepan/qwen2.5-128k-tiny-random", + "_task": "text-generation", + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "hidden_act": "silu", + "hidden_size": 8, + "initializer_range": 0.02, + "intermediate_size": 16, + "max_position_embeddings": 32768, + "max_window_layers": 1, + "model_type": "qwen2", + "neuron": { + "all_reduce_dtype": null, + "allow_flash_attention": true, + "attention_layout": "HSB", + "attn_output_transposed": false, + "auto_cast_type": "fp32", + "backend": "hlo", + "batch_size": 1, + "checkpoint_id": "yujiepan/qwen2.5-128k-tiny-random", + "checkpoint_revision": "c8296d4ca3f87782876d2382fbb6481d1beb8ef0", + "collectives_layout": "HSB", + "continuous_batching": false, + "fuse_qkv": false, + "group_query_attention": "shard-over-heads", + "log_softmax_scores": false, + "neuronxcc_version": "2.17.194.0+d312836f", + "optimum_neuron_version": "0.2.0.dev3", + "output_all_logits": false, + "sequence_length": 100, + "tp_degree": 2 + }, + "num_attention_heads": 4, + "num_hidden_layers": 2, + "num_key_value_heads": 2, + "rms_norm_eps": 1e-06, + "rope_scaling": { + "factor": 4.0, + "original_max_position_embeddings": 32768, + "rope_type": "yarn", + "type": "yarn" + }, + "rope_theta": 1000000.0, + "sliding_window": 131072, + "tie_word_embeddings": false, + "use_cache": true, + "use_sliding_window": false, + "vocab_size": 152064 +} \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..0137bc9ba0bb8adf071ca54f7c316c2fe64fd047 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206a7ad89370cff8d2b2322c1ac670c89f032f09dacf78c1919f6862a5f988f8 +size 20204 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..074eee18a25aa9686e94b28ff4533fe3dd89cf29 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_1649fc77b87fff02e370+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d594981e2da8b776c3c5a3eca2164c9f6fa6f0c449ac944452b14c94ddf0495 +size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..b491b19b467c4149e11536659bb757f969d67813 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bffb7434bff71e7ba712292397b2ad4ee6448cc362b3669d6140ae7eda9fed6f +size 21402 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..d951a263f32e0575642110794b9d2a00c1467db0 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_22cf23062ec53b3fd95d+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6112eb7624714812b25dc2f55104031955ba212a83c290b3e87880f61ae48063 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff index d8ddfa53ca48ff3a28df45a38b16e532b6fab764..c4691d37aaf060c98431cb366749ecdb7b96ebcc 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_24ff9ac2787ce9a1d276+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:be1fc03322aa9d157a6b41fd67890f055e0d0878b6504e5f47642cca280b170f +oid sha256:816f6e2b2800b0dd18941740a24948cd8febc13e0f8e9f734cc9f5dc87ad41fa size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e6e3e749231167973be1e74d4fac2cd7ad2ee71a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14f3f25ac84183e3e0fbaea932e3c43b3d7df2d165a2f3fd8d17bbb0d9b67100 +size 17475 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..becbd501c0718d4483c7bf54bc9d330e6a785e1d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_2ef52130792b59d66c66+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95ab464c4cf288bbb4eddc39060737a10a606d9a1780f619bd1249e31e77841c +size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff index e1a5d220f502c3948e982aabb3bdd5e01e8bdf09..24a073401b33f4294c479d13d76c47067c1f338f 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_320f2622d4d0c9fdd0f1+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:68e874b1f31bc45206f4c2049124f0985cad9a7f6c5b2b71ad453bf290cea9be +oid sha256:0d72740519c6f1609852cbefc2ca9c47c9c430eac2d564c11fb3e01d62dacc11 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3aa61c04bd8d9ca8722a+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3aa61c04bd8d9ca8722a+613edded/model.neff index 55798258f0031bcec994a620655577b5878213be..8f3e1451074be9f7f719eef0c15ec90c5188f1ac 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_3aa61c04bd8d9ca8722a+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3aa61c04bd8d9ca8722a+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:71a975bfc9afe131a009261a81dcde76b6f8e3de48a82027819f81062c48bc35 +oid sha256:d5c71c790f5cec922792760f98f020c80f8851e65d99cf2165fd2380ae3b9a07 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..235d59ffb22eac4d38831202f2394cf20f120cfa --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffcc61769d8fb9bea5e15c42d960c69b9df6f97061385d0bd0a21d0ce6906af6 +size 26028 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..f21b128b881e00b4784b4f95c785d82d5bd241eb --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_3da832fdaa3d62981800+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b76edbd85e8c2a4c9aa2e4f0a91f8a2d55f739330a4c09432d5068a8eb021e53 +size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..19ee2ce56e372faadab0d0eb539c4fd2881a5c36 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67d2c56e794836b16b020f5cd066ca11a1d29dafab34df3118d3d816e3ff6e95 +size 23565 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..b0910965fc1efb9c56ab0db96a6b944b6e0aae00 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_40b73cdf6e14999378ef+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5871a8f23388ad9e78e2f48f3ee955c4facce1a3f373c6980e68f9cbef93853f +size 164864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_48437cc74469a8ccaec8+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_48437cc74469a8ccaec8+613edded/model.neff index fe1adc1f864fa06c330d01cc082fcde19382a08b..ede25025aa105297b8f390d92a50a3bf9f1e8c9d 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_48437cc74469a8ccaec8+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_48437cc74469a8ccaec8+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:93a20c24604eaa08c2e14387740552dcccd1ea088a21a12050f0885a46a2ddf4 +oid sha256:58c71f97d235636814f05e8d6047fbe743ddb7e6d20f90577c8d29be05e7689d size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff index 2d38ae7ade72e4236a2fa677563f094e68fa46c8..494379b80a2638c600f0ec7516ff2459a14de5f8 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_48bfe9ceb9631fdca2d4+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:356a341c3e1907677aed4628bfaec17f0d2b48ac090addd2d8b1fa072f9332fb +oid sha256:c242498d423f976198e48db300828acb03aeac1809d796be2e6a923bfb44689c size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..23942f638bd29a30c4c39d3bbfbf9bb6be8ba782 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15bcc1c290cb31694bdf9dcca14c4212f94ac98633cf07e5f78c88252248395 +size 17129 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..973287ab9a2cff2f93dbc04b53aed4ac063c7278 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_4dea33d55b39527f7fc4+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda494af1d3d8fe727fd6f8b8632c99dae58cb97e60706daad7ed24c100aa459 +size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..3b4e7ea5755558eb24b7381a41d46c5758ca5c47 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0395aa664ed1ddbb5519230b5f4664bb55551ee04dbb00dee5498927b8c53f4 +size 20595 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..e65b52f53e3da34b57973fcfc059249ff7226ebb --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_54947fa9c379486e4f5b+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca8e32f83811391c47229b37a069f3e04202bd0b8df874d0638d0c49241e93d5 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6819e64fb96e87ffece0+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_6819e64fb96e87ffece0+613edded/model.neff index ab7550ec6fd0b50e17c4cec4783ce5e880728037..c099180afed92dd1784e7f6e709edb0e95a30a8e 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_6819e64fb96e87ffece0+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6819e64fb96e87ffece0+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:d5324e4e6db89b1e57c3b5a686220b043ff876db7db2ad3c578baaa18b48b385 +oid sha256:8b759b85a480af8a95b47df41a132f4fa1e2dfc1b6ab7712662c40a6fec780fc size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..a836ef47b71b43d82b2f930e493cccf128dfca6d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50e435aeef8bdd9674c2775e843d1719acfad33321f93d28422eceda1c8d898a +size 19475 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..16ef9fc03412e4f8370467536c6508f7b2068ae6 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_6f479fa0ca80b88a5b46+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08bb2544280493888a28c15041cacb76676e5b9d21b307ae93ea22ef42c55383 +size 164864 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..672f837d60308b6f194264f9372d1360eaf83702 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:635a56ee4821e472900e2f45aff06fca7b6436d644a90095b9c830f6deae7d18 +size 19832 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..9b9ac0cac399187be82318230a7fd3700155ca6f --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_83cb40c0c38bacf5b8fd+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e752ea5ae2b54d831b1fc55412033f8dff078e031e897fe39065590d6e03562d +size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..bcfde6e20c66b07f24c853a5f28354fe76bc7f1d --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c401c20ee313a4fda311fdf8ebd910b84f627ded8f6f3a17abb78ec208ffda +size 24382 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..99943dfadc9140d8e77aa139db7f67640f2c81ee --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_913f4e1e2b4632438fe9+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee0a64a5653b89693c7530e4b34af017b865b942035a891f7207dcf423e71b98 +size 154624 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff index e6350598cfe1fc85a90f7467ada8effa7c85dcec..78eaf3d20384828071cb3c1fed0b200372d888e7 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_c49c0c3715f68c22b32f+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:1c9c6956f1cef82f58f0b52dba3518ad4ee3d1388c4daeff4d71d9c75a66f6d5 +oid sha256:8ba4b9459507087b23f2b32a59c2f74aa3f276eb3086271e06f33469da50eee6 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff index b0fe205aa0f5e8d2dbf20fb9e38308dff024c673..4c2f11fa620ee86f455754d5a0be5f702336f3aa 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_cb16b651ea9d180d5cfd+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:29c3e4451a3e775865a77be7096705188d02a2c1f0ad2045dbdfeed636e96c1d +oid sha256:83d8ed4b67f52eff815a0995be0d5bebfd3f0bba38f620285c070d49aafe2a5c size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff index 5f20089774ba7fc192c991ab6cd48ff54118e883..5a6a296d8c13f447649058afea003f856b998700 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_de8368a717cfd6dfec57+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:84654b175befc1feb1d49424b9f04862113a8b52658ecce3de24dbe500b1c7eb +oid sha256:8f0f168589b268c08c82db181fdbff49cf3f20bf34e3296f7624e4613eac63a1 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff index 7815893c4829107b13f402985c564684a586ee61..f8aedad398c2228f6ed5efd4f62601afc0b23b17 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_df48af4bf01af7f3857e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:163100d52876f20578aadbbea622c29ff9c1fe5b20df2149e274c8fb7cc4229f +oid sha256:b86686143e8adfba9c0d950a405e8a6c1934a227faa64b402e5457c5be1920b8 size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff index 0740d390dc0dfc7a66839214c834589a5744767f..04a68757e8114ab8739ef18a46d1a8c995a5fda0 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e0765cf6df2204e3664e+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:632b08bab0a2c8592954816127b96dcfeae2d7b1d23cfcd45156af7c25558209 +oid sha256:9bb26efff1778505dd7037f18d58acb0906f2c53b16f4c92262ac0b93fde5005 size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e40769e5a35d3e5dacff+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e40769e5a35d3e5dacff+613edded/model.neff index e29e6b5b9228bf3e63a0433b616fe8b69b357b39..103c4b35086e98b60924f161a0b13ed1a3aeb87f 100644 --- a/neuronxcc-2.17.194.0+d312836f/MODULE_e40769e5a35d3e5dacff+613edded/model.neff +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e40769e5a35d3e5dacff+613edded/model.neff @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e92f1c2816dd237d52c18f60740f8679d4a26635a9f1958c1c36b6bb6fd521b4 +oid sha256:78ec86204ac598cb366d25c34dbbf5bce1d88312f385c12735beff3d15ee37a1 size 134144 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..e7e98abc16c79167b76d6d682779cd369bd99c37 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e882dda7ca8d1e7ddcf2c54143922356b4f41b29afbc979ecca776884fae42c +size 22951 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..77e3d6da2cafdcbee1fd0edc0d9f86da756602fd --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_e9bcfc17d832317203bd+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78a37c04af5640a6bd258a6eb5e82790e3771baf0e1a2e10073d7bb7c87bef8 +size 144384 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/compile_flags.json b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/compile_flags.json new file mode 100644 index 0000000000000000000000000000000000000000..0c655e4bcad17c00d4d9ec479b31fc9e637d4287 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/compile_flags.json @@ -0,0 +1 @@ +["--target=trn1", "--model-type=transformer", "--auto-cast=none", "--execute-repetition=1"] \ No newline at end of file diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.done b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.done new file mode 100644 index 0000000000000000000000000000000000000000..e69de29bb2d1d6434b8b29ae775ad8c2e48c5391 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.hlo_module.pb b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.hlo_module.pb new file mode 100644 index 0000000000000000000000000000000000000000..2df2ab269e3006b628a43a78c09f0fd04c07b48a --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.hlo_module.pb @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e6693f31ad55428431f8380303e8dc91ca44830232eaea952d4b260f95957fb +size 22558 diff --git a/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff new file mode 100644 index 0000000000000000000000000000000000000000..8d04d7b76a2c3689bbcfdac15738019a8f52fcc1 --- /dev/null +++ b/neuronxcc-2.17.194.0+d312836f/MODULE_fce469267b2ad1b5d80e+613edded/model.neff @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02e5df0a3f1e98520edadd58cfff703a85026324eda7c3e3a8b5bfb6612e6fd9 +size 154624