Synchronizing local compiler cache.

.gitattributes

@@ -10068,3 +10068,7 @@ neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/text_encoder_2/model.
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
 neuronxcc-2.19.8089.0+8ab9f450/MODULE_7c0a3faa643571c6da59/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/text_encoder_2/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/unet/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/vae_decoder/model.neuron filter=lfs diff=lfs merge=lfs -text
+neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/vae_encoder/model.neuron filter=lfs diff=lfs merge=lfs -text

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.0.dev5/stable-diffusion/stabilityai/stable-diffusion-xl-refiner-1.0/0181db83f04359c04c6d.json

@@ -0,0 +1,133 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "stabilityai/stable-diffusion-xl-refiner-1.0",
+  "_task": null,
+  "text_encoder_2": {
+    "architectures": [
+      "CLIPTextModelWithProjection"
+    ],
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "export_model_type": "clip-text-with-projection",
+    "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": "2.19.8089.0+8ab9f450",
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": false,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_sequence_length": 77,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_attention_heads": 20,
+    "num_hidden_layers": 32,
+    "output_hidden_states": true,
+    "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": "2.19.8089.0+8ab9f450",
+      "dynamic_batch_size": false,
+      "float_dtype": "fp32",
+      "inline_weights_to_neff": true,
+      "int_dtype": "int64",
+      "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_vae_scale_factor": 8,
+      "static_width": 128,
+      "task": "semantic-segmentation",
+      "tensor_parallel_size": 1
+    },
+    "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,
+    "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-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/model_index.json

@@ -0,0 +1,43 @@
+{
+  "_class_name": "StableDiffusionXLImg2ImgPipeline",
+  "_diffusers_version": "0.34.0",
+  "_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-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/scheduler/scheduler_config.json

@@ -0,0 +1,25 @@
+{
+  "_class_name": "EulerDiscreteScheduler",
+  "_diffusers_version": "0.34.0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "final_sigmas_type": "zero",
+  "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_beta_sigmas": false,
+  "use_exponential_sigmas": false,
+  "use_karras_sigmas": false
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/text_encoder_2/config.json

@@ -0,0 +1,54 @@
+{
+  "_attn_implementation_autoset": true,
+  "architectures": [
+    "CLIPTextModelWithProjection"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "export_model_type": "clip-text-with-projection",
+  "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": "2.19.8089.0+8ab9f450",
+    "dynamic_batch_size": false,
+    "float_dtype": "fp32",
+    "inline_weights_to_neff": false,
+    "input_names": [
+      "input_ids"
+    ],
+    "int_dtype": "int64",
+    "model_type": "clip-text-with-projection",
+    "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,
+    "task": "feature-extraction",
+    "tensor_parallel_size": 1
+  },
+  "num_attention_heads": 20,
+  "num_hidden_layers": 32,
+  "output_hidden_states": true,
+  "pad_token_id": 1,
+  "projection_dim": 1280,
+  "torch_dtype": "float32",
+  "torchscript": true,
+  "transformers_version": "4.51.3",
+  "vocab_size": 49408
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/text_encoder_2/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d80291f344934bf27d1421f152acc09b928309af7d5e46e4e01be44ad2e07f4
+size 2801581621

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/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-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/tokenizer_2/tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "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",
+  "extra_special_tokens": {},
+  "model_max_length": 77,
+  "pad_token": "!",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/unet/config.json

@@ -0,0 +1,111 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_commit_hash": null,
+  "_diffusers_version": "0.34.0",
+  "_use_default_values": [
+    "attention_type",
+    "dropout",
+    "reverse_transformer_layers_per_block"
+  ],
+  "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": "2.19.8089.0+8ab9f450",
+    "dynamic_batch_size": false,
+    "float_dtype": "fp32",
+    "inline_weights_to_neff": true,
+    "input_names": [
+      "sample",
+      "timestep",
+      "encoder_hidden_states",
+      "text_embeds",
+      "time_ids"
+    ],
+    "int_dtype": "int64",
+    "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_vae_scale_factor": 8,
+    "static_width": 128,
+    "task": "semantic-segmentation",
+    "tensor_parallel_size": 1
+  },
+  "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,
+  "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-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/unet/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96f273735e5aa2db00867c1cd6019875d24f2d103494f31ceee529aca8fa97db
+size 3686370617

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/vae_decoder/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_commit_hash": null,
+  "_diffusers_version": "0.34.0",
+  "_use_default_values": [
+    "mid_block_add_attention",
+    "use_post_quant_conv",
+    "use_quant_conv",
+    "latents_std",
+    "latents_mean",
+    "shift_factor"
+  ],
+  "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,
+  "mid_block_add_attention": true,
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.19.8089.0+8ab9f450",
+    "dynamic_batch_size": false,
+    "float_dtype": "fp32",
+    "inline_weights_to_neff": true,
+    "input_names": [
+      "latent_sample"
+    ],
+    "int_dtype": "int64",
+    "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,
+    "task": "semantic-segmentation",
+    "tensor_parallel_size": 1
+  },
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "shift_factor": null,
+  "transformers_version": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/vae_decoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4228ba12b95476de39f3d399cdd3ede0923a3acc87c745efc695ed60031c1c
+size 370909427

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/vae_encoder/config.json

@@ -0,0 +1,73 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_commit_hash": null,
+  "_diffusers_version": "0.34.0",
+  "_use_default_values": [
+    "mid_block_add_attention",
+    "use_post_quant_conv",
+    "use_quant_conv",
+    "latents_std",
+    "latents_mean",
+    "shift_factor"
+  ],
+  "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,
+  "mid_block_add_attention": true,
+  "neuron": {
+    "auto_cast": "matmul",
+    "auto_cast_type": "bf16",
+    "compiler_type": "neuronx-cc",
+    "compiler_version": "2.19.8089.0+8ab9f450",
+    "dynamic_batch_size": false,
+    "float_dtype": "fp32",
+    "inline_weights_to_neff": true,
+    "input_names": [
+      "sample"
+    ],
+    "int_dtype": "int64",
+    "model_type": "vae-encoder",
+    "optlevel": "2",
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_names": [
+      "latent_parameters"
+    ],
+    "static_batch_size": 1,
+    "static_height": 1024,
+    "static_num_channels": 3,
+    "static_width": 1024,
+    "task": "semantic-segmentation",
+    "tensor_parallel_size": 1
+  },
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 1024,
+  "scaling_factor": 0.13025,
+  "shift_factor": null,
+  "transformers_version": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_0181db83f04359c04c6d/vae_encoder/model.neuron

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71f062b8d33b763a394a6f12dbfb4cc1899f5d2eced27e2019b675b15ceb9d2d
+size 222984881