Synchronizing local compiler cache.

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev2/inference/stable-diffusion/stabilityai/sdxl-turbo/351b361df13ba0a651c3.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"_attn_implementation_autoset": true, "architectures": ["CLIPTextModel"], "attention_dropout": 0.0, "dropout": 0.0, "hidden_act": "quick_gelu", "hidden_size": 768, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 3072, "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": "2.16.372.0+4a9b2326", "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, "tensor_parallel_size": 1}, "num_attention_heads": 12, "num_hidden_layers": 12, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 49408}, "text_encoder_2": {"_attn_implementation_autoset": true, "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": "2.16.372.0+4a9b2326", "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, "tensor_parallel_size": 1}, "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": [5, 10, 20], "attention_type": "default", "block_out_channels": [320, 640, 1280], "center_input_sample": false, "class_embed_type": null, "class_embeddings_concat": false, "conv_in_kernel": 3, "conv_out_kernel": 3, "cross_attention_dim": 2048, "cross_attention_norm": null, "down_block_types": ["DownBlock2D", "CrossAttnDownBlock2D", "CrossAttnDownBlock2D"], "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": "2.16.372.0+4a9b2326", "dynamic_batch_size": false, "inline_weights_to_neff": true, "optlevel": "2", "output_attentions": false, "output_hidden_states": false, "static_batch_size": 1, "static_height": 96, "static_num_channels": 4, "static_sequence_length": 77, "static_vae_scale_factor": 8, "static_width": 96, "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": 2816, "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, 2, 10], "up_block_types": ["CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": null, "use_linear_projection": true}}

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/model_index.json

@@ -1,7 +1,7 @@
 {
   "_class_name": "StableDiffusionXLPipeline",
   "_diffusers_version": "0.30.3",
-  "_name_or_path": "stabilityai/stable-diffusion-xl-base-1.0",
+  "_name_or_path": "stabilityai/sdxl-turbo",
   "feature_extractor": [
     null,
     null
@@ -13,7 +13,7 @@
   ],
   "scheduler": [
     "diffusers",
-    "EulerDiscreteScheduler"
+    "EulerAncestralDiscreteScheduler"
   ],
   "text_encoder": [
     "transformers",

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/scheduler/scheduler_config.json

@@ -1,23 +1,18 @@
 {
-  "_class_name": "EulerDiscreteScheduler",
+  "_class_name": "EulerAncestralDiscreteScheduler",
   "_diffusers_version": "0.30.3",
   "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_karras_sigmas": false
+  "timestep_spacing": "trailing",
+  "trained_betas": null
 }

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/text_encoder/config.json

@@ -1,6 +1,6 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder",
+  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--sdxl-turbo/snapshots/71153311d3dbb46851df1931d3ca6e939de83304/text_encoder",
   "architectures": [
     "CLIPTextModel"
   ],

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:310f16716b1af8a34703824c73cd35f6316bd8222f9026d6b1ca058723c6d093
+oid sha256:bf2d938f2043faf162634a82fe9c85f6f25d71bc8e42207fbc80d0c534beb66e
 size 495981433

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/text_encoder_2/config.json

@@ -1,6 +1,6 @@
 {
   "_attn_implementation_autoset": true,
-  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/text_encoder_2",
+  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--sdxl-turbo/snapshots/71153311d3dbb46851df1931d3ca6e939de83304/text_encoder_2",
   "architectures": [
     "CLIPTextModelWithProjection"
   ],

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0450017750428453d8c6459b582d8dafcfd67a02a9233d76359a036a0eb24b3
+oid sha256:95ffa9089178d02623ae6a5207fa125fae8c8a2d9182588dff0e2da00752f96e
 size 2800105963

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/tokenizer/special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/tokenizer_2/special_tokens_map.json

@@ -13,7 +13,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "!",
+  "pad_token": {
+    "content": "!",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/unet/config.json

@@ -2,12 +2,7 @@
   "_class_name": "UNet2DConditionModel",
   "_commit_hash": null,
   "_diffusers_version": "0.30.3",
-  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/unet",
-  "_use_default_values": [
-    "attention_type",
-    "dropout",
-    "reverse_transformer_layers_per_block"
-  ],
+  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--sdxl-turbo/snapshots/71153311d3dbb46851df1931d3ca6e939de83304/unet",
   "act_fn": "silu",
   "addition_embed_type": "text_time",
   "addition_embed_type_num_heads": 64,
@@ -87,7 +82,7 @@
   "resnet_skip_time_act": false,
   "resnet_time_scale_shift": "default",
   "reverse_transformer_layers_per_block": null,
-  "sample_size": 128,
+  "sample_size": 64,
   "task": "semantic-segmentation",
   "time_cond_proj_dim": null,
   "time_embedding_act_fn": null,

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4becde7c70226cc11d449930f2aa62d6f68b981b4231a173c6f78077ad4ba69b
-size 4155440509
+oid sha256:e97ee47a5107f996fcde52a4143b534c8ce3cc1bffeebf23ad27f922ba3a48ed
+size 4155522429

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/vae_decoder/config.json

@@ -2,14 +2,14 @@
   "_class_name": "AutoencoderKL",
   "_commit_hash": null,
   "_diffusers_version": "0.30.3",
-  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/vae",
+  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--sdxl-turbo/snapshots/71153311d3dbb46851df1931d3ca6e939de83304/vae",
   "_use_default_values": [
-    "use_quant_conv",
+    "shift_factor",
     "latents_std",
-    "mid_block_add_attention",
     "latents_mean",
     "use_post_quant_conv",
-    "shift_factor"
+    "use_quant_conv",
+    "mid_block_add_attention"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96e2b5fdbe83338a6d72040079ad262a833b6b7d97d972d0d0345dc297d09ba9
+oid sha256:10079a7d328ce10a779d11191c727ae5442c3f53262e259b67281a32b150d1b9
 size 436957747

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/vae_encoder/config.json

@@ -2,14 +2,14 @@
   "_class_name": "AutoencoderKL",
   "_commit_hash": null,
   "_diffusers_version": "0.30.3",
-  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/vae",
+  "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--sdxl-turbo/snapshots/71153311d3dbb46851df1931d3ca6e939de83304/vae",
   "_use_default_values": [
-    "use_quant_conv",
+    "shift_factor",
     "latents_std",
-    "mid_block_add_attention",
     "latents_mean",
     "use_post_quant_conv",
-    "shift_factor"
+    "use_quant_conv",
+    "mid_block_add_attention"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.16.372.0+4a9b2326/MODULE_351b361df13ba0a651c3/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48179322e69e05922620df64a5efe8ab26ca3216cdcc145f4f22f19432358986
+oid sha256:9dbe8619ec74d85c4f8f6e93307d97419b4b03603bdeb810083a497268f0f643
 size 248480307