Synchronizing local compiler cache.

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev5/stable-diffusion/stabilityai/sdxl-turbo/c5e254d87b22ca9cbf1f.json

@@ -0,0 +1,173 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "stabilityai/sdxl-turbo",
+  "_task": null,
+  "text_encoder": {
+    "architectures": [
+      "CLIPTextModel"
+    ],
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "export_model_type": "clip-text-model",
+    "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": "2.19.8089.0+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": 12,
+    "num_hidden_layers": 12,
+    "output_hidden_states": true,
+    "return_dict": false,
+    "vocab_size": 49408
+  },
+  "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,
+    "return_dict": false,
+    "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": "2.19.8089.0+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,
+    "output_attentions": false,
+    "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-2.19.8089.0+8ab9f450/MODULE_c5e254d87b22ca9cbf1f/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b38e9d0e9289b054790e8c5f638bf73ee39ea67625fe78bf81d74502e5dc140f
+oid sha256:1037828e7720f54212a74cdf385a78bf982a39d0debe4e277ee3532bc24670ef
 size 496156793

neuronxcc-2.19.8089.0+8ab9f450/MODULE_c5e254d87b22ca9cbf1f/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e50726ddb05ad193d79d560b4286e1f4d68015ec9424e9dd1f438ebbeb37a11
+oid sha256:3c95fd1ab2feaf105d891297163460ab901b32e121a2a71cb91faf964284a0db
 size 2801804587

neuronxcc-2.19.8089.0+8ab9f450/MODULE_c5e254d87b22ca9cbf1f/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daeeebbe775eed2724809f056e8cc70276abc6c45fe247fcf8a8fb0b8a8a3234
+oid sha256:a325278abd59189bd6ef04f2aaf8066676e7a24568633417750ba99849a329a8
 size 4175474813

neuronxcc-2.19.8089.0+8ab9f450/MODULE_c5e254d87b22ca9cbf1f/vae_decoder/config.json

@@ -3,11 +3,11 @@
   "_diffusers_version": "0.35.1",
   "_use_default_values": [
     "mid_block_add_attention",
-    "shift_factor",
+    "latents_mean",
     "use_quant_conv",
     "latents_std",
     "use_post_quant_conv",
-    "latents_mean"
+    "shift_factor"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_c5e254d87b22ca9cbf1f/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ffa5bde021e6f727a275035a5d06f96270173817f68edd96f82aac52fed8e0
+oid sha256:66fbbab14c76b0101026e8dcc40bd20b2eeb7980e7b3a262c6cf365be2bb3401
 size 370909427

neuronxcc-2.19.8089.0+8ab9f450/MODULE_c5e254d87b22ca9cbf1f/vae_encoder/config.json

@@ -3,11 +3,11 @@
   "_diffusers_version": "0.35.1",
   "_use_default_values": [
     "mid_block_add_attention",
-    "shift_factor",
+    "latents_mean",
     "use_quant_conv",
     "latents_std",
     "use_post_quant_conv",
-    "latents_mean"
+    "shift_factor"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_c5e254d87b22ca9cbf1f/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd1b33da9a652253dea4eed49083582efa0f458d827f906663f777172d93bfb
+oid sha256:ec03524c636003b43e21fc7154571ade1980934673173742d1cb1e27337f528a
 size 222984883