Synchronizing local compiler cache.

.gitattributes

@@ -1826,3 +1826,7 @@ neuronxcc-2.12.68.0+4480452af/MODULE_cf0089936bbe59ef14dd/text_encoder/model.neu
 neuronxcc-2.12.68.0+4480452af/MODULE_cf0089936bbe59ef14dd/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.68.0+4480452af/MODULE_cf0089936bbe59ef14dd/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.68.0+4480452af/MODULE_cf0089936bbe59ef14dd/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/text_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.12.68.0+4480452af/0_REGISTRY/0.0.21.dev0/inference/stable-diffusion/stabilityai/stable-diffusion-2-1/0a2a84e73bbfccb069e0.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "gelu", "hidden_size": 1024, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-05, "max_position_embeddings": 77, "model_type": "clip_text_model", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_sequence_length": 77}, "num_attention_heads": 16, "num_hidden_layers": 23, "task": "feature-extraction", "vocab_size": 49408}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": null, "addition_embed_type_num_heads": 64, "addition_time_embed_dim": null, "attention_head_dim": [5, 10, 20, 20], "attention_type": "default", "block_out_channels": [320, 640, 1280, 1280], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 1024, "cross_attention_norm": null, "down_block_types": ["CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D", "DownBlock2D"], "downsample_padding": 1, "dropout": 0.0, "dual_cross_attention": false, "encoder_hid_dim": null, "encoder_hid_dim_type": null, "flip_sin_to_cos": true, "freq_shift": 0, "in_channels": 4, "layers_per_block": 2, "mid_block_only_cross_attention": null, "mid_block_scale_factor": 1, "mid_block_type": "UNetMidBlock2DCrossAttn", "neuron": {"auto_cast": "matmul", "auto_cast_type": "bf16", "compiler_type": "neuronx-cc", "compiler_version": "2.12.68.0+4480452af", "dynamic_batch_size": false, "inline_weights_to_neff": false, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 64, "static_num_channels": 4, "static_sequence_length": 77, "static_width": 64}, "norm_eps": 1e-05, "norm_num_groups": 32, "num_attention_heads": null, "num_class_embeds": null, "only_cross_attention": false, "out_channels": 4, "projection_class_embeddings_input_dim": null, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "time_cond_proj_dim": null, "time_embedding_act_fn": null, "time_embedding_dim": null, "time_embedding_type": "positional", "timestep_post_act": null, "transformer_layers_per_block": 1, "up_block_types": ["UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D"], "upcast_attention": true, "use_linear_projection": true}}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/feature_extractor/preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/model_index.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "stabilityai/stable-diffusion-2-1",
+  "feature_extractor": [
+    "transformers",
+    "CLIPImageProcessor"
+  ],
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_safety_checker": false,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/scheduler/scheduler_config.json

@@ -0,0 +1,20 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.27.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "clip_sample_range": 1.0,
+  "dynamic_thresholding_ratio": 0.995,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "thresholding": false,
+  "timestep_spacing": "leading",
+  "trained_betas": null
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/text_encoder/config.json

@@ -0,0 +1,48 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/text_encoder",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.12.68.0+4480452af",
+    "dynamic_batch_size": false,
+    "inline_weights_to_neff": false,
+    "input_names": [
+      "input_ids"
+    ],
+    "model_type": "clip-text-model",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "last_hidden_state",
+      "pooler_output"
+    ],
+    "static_batch_size": 1,
+    "static_sequence_length": 77
+  },
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "task": "feature-extraction",
+  "torch_dtype": "float32",
+  "torchscript": true,
+  "transformers_version": "4.36.2",
+  "vocab_size": 49408
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/text_encoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebb71c712325e5a3a328975639c3fcee672b95e8486ed30465f59bd0fefffeb9
+size 1375267100

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "!",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/tokenizer/tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "!",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/unet/config.json

@@ -0,0 +1,129 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_commit_hash": null,
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/unet",
+  "_use_default_values": [
+    "cross_attention_norm",
+    "conv_in_kernel",
+    "mid_block_type",
+    "transformer_layers_per_block",
+    "reverse_transformer_layers_per_block",
+    "encoder_hid_dim",
+    "time_cond_proj_dim",
+    "mid_block_only_cross_attention",
+    "attention_type",
+    "timestep_post_act",
+    "time_embedding_act_fn",
+    "encoder_hid_dim_type",
+    "dropout",
+    "addition_embed_type",
+    "resnet_skip_time_act",
+    "resnet_out_scale_factor",
+    "conv_out_kernel",
+    "time_embedding_dim",
+    "num_attention_heads",
+    "class_embeddings_concat",
+    "resnet_time_scale_shift",
+    "projection_class_embeddings_input_dim",
+    "addition_embed_type_num_heads",
+    "addition_time_embed_dim",
+    "time_embedding_type",
+    "class_embed_type"
+  ],
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1024,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.12.68.0+4480452af",
+    "dynamic_batch_size": false,
+    "inline_weights_to_neff": false,
+    "input_names": [
+      "sample",
+      "timestep",
+      "encoder_hidden_states"
+    ],
+    "model_type": "unet",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "sample"
+    ],
+    "static_batch_size": 1,
+    "static_height": 64,
+    "static_num_channels": 4,
+    "static_sequence_length": 77,
+    "static_width": 64
+  },
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 96,
+  "task": "semantic-segmentation",
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "transformers_version": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": true,
+  "use_linear_projection": true
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/unet/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c6714fe74a0004f47bf2cca4e194d5b0d79fadfae316b29ec0d6d2701dea56
+size 3566173190

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/vae_decoder/config.json

@@ -0,0 +1,65 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_commit_hash": null,
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/vae",
+  "_use_default_values": [
+    "scaling_factor",
+    "force_upcast",
+    "latents_mean",
+    "latents_std"
+  ],
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.12.68.0+4480452af",
+    "dynamic_batch_size": false,
+    "inline_weights_to_neff": false,
+    "input_names": [
+      "latent_sample"
+    ],
+    "model_type": "vae-decoder",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "sample"
+    ],
+    "static_batch_size": 1,
+    "static_height": 64,
+    "static_num_channels": 4,
+    "static_width": 64
+  },
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
+  "task": "semantic-segmentation",
+  "transformers_version": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/vae_decoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52026978c6153b984497410e422b68dcbc1ded7113dbc2da994ef886e17014b2
+size 380238844

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/vae_encoder/config.json

@@ -0,0 +1,65 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_commit_hash": null,
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-2-1/snapshots/5cae40e6a2745ae2b01ad92ae5043f95f23644d6/vae",
+  "_use_default_values": [
+    "scaling_factor",
+    "force_upcast",
+    "latents_mean",
+    "latents_std"
+  ],
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.12.68.0+4480452af",
+    "dynamic_batch_size": false,
+    "inline_weights_to_neff": false,
+    "input_names": [
+      "sample"
+    ],
+    "model_type": "vae-encoder",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "latent_sample"
+    ],
+    "static_batch_size": 1,
+    "static_height": 512,
+    "static_num_channels": 3,
+    "static_width": 512
+  },
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 768,
+  "scaling_factor": 0.18215,
+  "task": "semantic-segmentation",
+  "transformers_version": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

neuronxcc-2.12.68.0+4480452af/MODULE_0a2a84e73bbfccb069e0/vae_encoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd454549eb9c74b03a8b423dae941f3852450f33fafaa74e04426e89ee682d4
+size 237903262