Synchronizing local compiler cache.

.gitattributes

@@ -1848,3 +1848,7 @@ neuronxcc-2.12.68.0+4480452af/MODULE_cb10fa3dd06630c3a41b/text_encoder_2/model.n
 neuronxcc-2.12.68.0+4480452af/MODULE_cb10fa3dd06630c3a41b/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.68.0+4480452af/MODULE_cb10fa3dd06630c3a41b/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.12.68.0+4480452af/MODULE_cb10fa3dd06630c3a41b/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/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-xl-refiner-1.0/c658f424c983d468243e.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder_2": {"architectures": ["CLIPTextModelWithProjection"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "gelu", "hidden_size": 1280, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 5120, "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": 20, "num_hidden_layers": 32, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 49408}, "unet": {"_class_name": "UNet2DConditionModel", "act_fn": "silu", "addition_embed_type": "text_time", "addition_embed_type_num_heads": 64, "addition_time_embed_dim": 256, "attention_head_dim": [6, 12, 24, 24], "attention_type": "default", "block_out_channels": [384, 768, 1536, 1536], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 1280, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "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": 128, "static_num_channels": 4, "static_sequence_length": 77, "static_width": 128}, "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": 2560, "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": 4, "up_block_types": ["UpBlock2D", "CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": null, "use_linear_projection": true}}

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/model_index.json

@@ -0,0 +1,43 @@
+{
+  "_class_name": "StableDiffusionXLImg2ImgPipeline",
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "stabilityai/stable-diffusion-xl-refiner-1.0",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "force_zeros_for_empty_prompt": false,
+  "image_encoder": [
+    null,
+    null
+  ],
+  "requires_aesthetics_score": true,
+  "scheduler": [
+    "diffusers",
+    "EulerDiscreteScheduler"
+  ],
+  "text_encoder": [
+    null,
+    null
+  ],
+  "text_encoder_2": [
+    "transformers",
+    "CLIPTextModelWithProjection"
+  ],
+  "tokenizer": [
+    null,
+    null
+  ],
+  "tokenizer_2": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/scheduler/scheduler_config.json

@@ -0,0 +1,22 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.27.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "interpolation_type": "linear",
+  "num_train_timesteps": 1000,
+  "prediction_type": "epsilon",
+  "rescale_betas_zero_snr": false,
+  "sample_max_value": 1.0,
+  "set_alpha_to_one": false,
+  "sigma_max": null,
+  "sigma_min": null,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "timestep_spacing": "leading",
+  "timestep_type": "discrete",
+  "trained_betas": null,
+  "use_karras_sigmas": false
+}

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/text_encoder_2/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-refiner-1.0/snapshots/5d4cfe854c9a9a87939ff3653551c2b3c99a4356/text_encoder_2",
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1280,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "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": [
+      "text_embeds",
+      "last_hidden_state",
+      "hidden_states"
+    ],
+    "static_batch_size": 1,
+    "static_sequence_length": 77
+  },
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "task": "feature-extraction",
+  "torch_dtype": "float16",
+  "torchscript": true,
+  "transformers_version": "4.36.2",
+  "vocab_size": 49408
+}

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/text_encoder_2/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb929c5a9257a797b1b8b2931b4a221559bc524eed270127bc6ba3b0be840e97
+size 2805503411

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/tokenizer_2/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_c658f424c983d468243e/tokenizer_2/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_c658f424c983d468243e/unet/config.json

@@ -0,0 +1,108 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_commit_hash": null,
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-refiner-1.0/snapshots/5d4cfe854c9a9a87939ff3653551c2b3c99a4356/unet",
+  "_use_default_values": [
+    "reverse_transformer_layers_per_block",
+    "dropout",
+    "attention_type"
+  ],
+  "act_fn": "silu",
+  "addition_embed_type": "text_time",
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": 256,
+  "attention_head_dim": [
+    6,
+    12,
+    24,
+    24
+  ],
+  "attention_type": "default",
+  "block_out_channels": [
+    384,
+    768,
+    1536,
+    1536
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 1280,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "DownBlock2D",
+    "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",
+      "text_embeds",
+      "time_ids"
+    ],
+    "model_type": "unet",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "sample"
+    ],
+    "static_batch_size": 1,
+    "static_height": 128,
+    "static_num_channels": 4,
+    "static_sequence_length": 77,
+    "static_width": 128
+  },
+  "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": 2560,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 128,
+  "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": 4,
+  "transformers_version": null,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "UpBlock2D"
+  ],
+  "upcast_attention": null,
+  "use_linear_projection": true
+}

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/unet/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0f2e4d6dfc18515f108425473deaa87a6fda5f236a0d13595a010a2500c980
+size 9113229836

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_decoder/config.json

@@ -0,0 +1,63 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_commit_hash": null,
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-refiner-1.0/snapshots/5d4cfe854c9a9a87939ff3653551c2b3c99a4356/vae",
+  "_use_default_values": [
+    "latents_std",
+    "latents_mean"
+  ],
+  "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": 128,
+    "static_num_channels": 4,
+    "static_width": 128
+  },
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "task": "semantic-segmentation",
+  "transformers_version": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_decoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155dc6b9797c1e1ea74f2833de0e104be8ec730afb7e063062f2d14249983626
+size 912124924

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_encoder/config.json

@@ -0,0 +1,63 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_commit_hash": null,
+  "_diffusers_version": "0.27.2",
+  "_name_or_path": "/home/ubuntu/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-refiner-1.0/snapshots/5d4cfe854c9a9a87939ff3653551c2b3c99a4356/vae",
+  "_use_default_values": [
+    "latents_std",
+    "latents_mean"
+  ],
+  "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": 1024,
+    "static_num_channels": 3,
+    "static_width": 1024
+  },
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "task": "semantic-segmentation",
+  "transformers_version": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

neuronxcc-2.12.68.0+4480452af/MODULE_c658f424c983d468243e/vae_encoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbace1a1be42ebb381da491d7da361522c802af1028e5a3be5eeceb965b903d9
+size 471549342