Synchronizing local compiler cache.

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev0/stable-diffusion/stabilityai/stable-diffusion-xl-base-1.0/a8218e1ae23f2aaf8834.json

@@ -0,0 +1,162 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "stabilityai/stable-diffusion-xl-base-1.0",
+  "_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": 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": 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_a8218e1ae23f2aaf8834/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97360b81ddac5454f2eef15f641faae04dc606990193e03b3d7523b679108dd
+oid sha256:be680084c85bb56fd1a99e48f726f79795a5279b3291ba8637c4a78bb11662d2
 size 495950713

neuronxcc-2.17.194.0+d312836f/MODULE_a8218e1ae23f2aaf8834/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcd80ffa8c588df092ace127295bb6978da2fe58a3ba56234f699ab8b3b1377d
+oid sha256:4552cc5fdf32af324cdec926d8bb68ba3611f7bc22258e7f8cfb1a4f198d8ea7
 size 2801222123

neuronxcc-2.17.194.0+d312836f/MODULE_a8218e1ae23f2aaf8834/unet/config.json

@@ -3,9 +3,9 @@
   "_commit_hash": null,
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
-    "attention_type",
     "reverse_transformer_layers_per_block",
-    "dropout"
+    "dropout",
+    "attention_type"
   ],
   "act_fn": "silu",
   "addition_embed_type": "text_time",

neuronxcc-2.17.194.0+d312836f/MODULE_a8218e1ae23f2aaf8834/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063f3decf3c51c802e9d7c19e1a97624dcecb298b735a31b5b6eae553f441114
+oid sha256:714452194ce02bd9f3c514ef41b85dcf75503e0edddaaf61a80942cee76ef583
 size 4173340029

neuronxcc-2.17.194.0+d312836f/MODULE_a8218e1ae23f2aaf8834/vae_decoder/config.json

@@ -4,11 +4,11 @@
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
     "mid_block_add_attention",
+    "use_quant_conv",
     "latents_std",
+    "use_post_quant_conv",
     "shift_factor",
-    "latents_mean",
-    "use_quant_conv",
-    "use_post_quant_conv"
+    "latents_mean"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.17.194.0+d312836f/MODULE_a8218e1ae23f2aaf8834/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0212c8157e7265063f36a48860a34333d6b1bc4e96de424e32e86ef86adf77c6
+oid sha256:0f0ab40923a8d0542ea51bd8d9953b0a1719db4e7519c40376f34830ad6c6060
 size 749922867

neuronxcc-2.17.194.0+d312836f/MODULE_a8218e1ae23f2aaf8834/vae_encoder/config.json

@@ -4,11 +4,11 @@
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
     "mid_block_add_attention",
+    "use_quant_conv",
     "latents_std",
+    "use_post_quant_conv",
     "shift_factor",
-    "latents_mean",
-    "use_quant_conv",
-    "use_post_quant_conv"
+    "latents_mean"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.17.194.0+d312836f/MODULE_a8218e1ae23f2aaf8834/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:933b2df37c32fc2c5d72b9a005b3ae0b78ed0a3fbaf18a1b6c772bfb35b1f58a
+oid sha256:9ea0d1727a0e19a6c6123fd2398205238a7bb4d36c1d9412362f59fa0bfbc1cb
 size 382102067