Synchronizing local compiler cache.

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev4/stable-diffusion/stabilityai/sdxl-turbo/c4162c03a5bca6d7620e.json

@@ -0,0 +1,162 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "stabilityai/sdxl-turbo",
+  "_task": null,
+  "text_encoder": {
+    "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": "2.17.194.0+d312836f",
+      "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,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "output_hidden_states": true,
+    "vocab_size": 49408
+  },
+  "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": "2.17.194.0+d312836f",
+      "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,
+      "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": [
+      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": "2.17.194.0+d312836f",
+      "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,
+      "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": 2816,
+    "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": [
+      1,
+      2,
+      10
+    ],
+    "up_block_types": [
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D",
+      "UpBlock2D"
+    ],
+    "upcast_attention": null,
+    "use_linear_projection": true
+  }
+}

neuronxcc-2.17.194.0+d312836f/MODULE_c4162c03a5bca6d7620e/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b06e47e21ffb869d1ea14f2c214a6f3f9ac318a657d0826cb672a14b570b1d82
+oid sha256:0f7394ce24b82b25da26e8b8ceb37bbc41fe281d7e08d59fdf0396cb22d357a7
 size 495950649

neuronxcc-2.17.194.0+d312836f/MODULE_c4162c03a5bca6d7620e/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4588f57683173b6de48513709970d9b5626af7a15f0e4399dc1629395183e2d5
+oid sha256:99ef153a1400658d0be9f943a67be6e32f4ae05930ac30a3cacbf69160129de4
 size 2801222123

neuronxcc-2.17.194.0+d312836f/MODULE_c4162c03a5bca6d7620e/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a8144f92e7c6719c38473410958bfe3a2b1076146067e3b7cd3f15e23cfc2d0
+oid sha256:30de0423291f38222dbce50ae7989dcf8a00bb01e90c6d43509cf317b5632493
 size 4156474685

neuronxcc-2.17.194.0+d312836f/MODULE_c4162c03a5bca6d7620e/vae_decoder/config.json

@@ -4,12 +4,12 @@
   "_diffusers_version": "0.30.3",
   "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--sdxl-turbo/snapshots/71153311d3dbb46851df1931d3ca6e939de83304/vae",
   "_use_default_values": [
-    "mid_block_add_attention",
-    "use_quant_conv",
-    "latents_mean",
     "latents_std",
     "use_post_quant_conv",
-    "shift_factor"
+    "shift_factor",
+    "latents_mean",
+    "mid_block_add_attention",
+    "use_quant_conv"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.17.194.0+d312836f/MODULE_c4162c03a5bca6d7620e/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9638e64a6fe9fb8949375315d80107852382a82ceda886377d55600fd6dbe7b
+oid sha256:105a7027a726e87564fe8174301cb8a9614eb1542dc553afcd236ae19dc185b9
 size 509313587

neuronxcc-2.17.194.0+d312836f/MODULE_c4162c03a5bca6d7620e/vae_encoder/config.json

@@ -4,12 +4,12 @@
   "_diffusers_version": "0.30.3",
   "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--sdxl-turbo/snapshots/71153311d3dbb46851df1931d3ca6e939de83304/vae",
   "_use_default_values": [
-    "mid_block_add_attention",
-    "use_quant_conv",
-    "latents_mean",
     "latents_std",
     "use_post_quant_conv",
-    "shift_factor"
+    "shift_factor",
+    "latents_mean",
+    "mid_block_add_attention",
+    "use_quant_conv"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.17.194.0+d312836f/MODULE_c4162c03a5bca6d7620e/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71294ce2d791c789e8149e954e8b7d4989e7ac1e20c00f6c2713376248fa529a
+oid sha256:3a2f0f62b95ebc64fd5770797a74f83ce80d21754f3a3d590ca3eb3c8bdf60ad
 size 285682227