Synchronizing local compiler cache.

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev5/stable-diffusion/stabilityai/stable-diffusion-xl-refiner-1.0/006ebbe04966f503c7ba.json

@@ -0,0 +1,135 @@
+{
+  "_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,
+    "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": [
+      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,
+    "output_attentions": false,
+    "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_006ebbe04966f503c7ba/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a712b91bfd3af01f0b8b264731e37c9f62868f9fb0a61b906f679796c6cd03
+oid sha256:ecceae0560a733c04bfc128a5c62a9a09cb408cbefc88bf4f18c32348be0caf4
 size 2801803637

neuronxcc-2.19.8089.0+8ab9f450/MODULE_006ebbe04966f503c7ba/unet/config.json

@@ -3,8 +3,8 @@
   "_diffusers_version": "0.35.1",
   "_use_default_values": [
     "attention_type",
-    "dropout",
-    "reverse_transformer_layers_per_block"
+    "reverse_transformer_layers_per_block",
+    "dropout"
   ],
   "act_fn": "silu",
   "addition_embed_type": "text_time",

neuronxcc-2.19.8089.0+8ab9f450/MODULE_006ebbe04966f503c7ba/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28065f3a89861e3eae0830b960a86cea5c33b2a1f31967c3f294255040393fcd
+oid sha256:7ab064b3639d80e94032b624e100a67e823d7cacd72799ea254dc6e9bd4d03cb
 size 3686370617

neuronxcc-2.19.8089.0+8ab9f450/MODULE_006ebbe04966f503c7ba/vae_decoder/config.json

@@ -2,12 +2,12 @@
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.35.1",
   "_use_default_values": [
-    "use_quant_conv",
     "mid_block_add_attention",
     "shift_factor",
-    "latents_mean",
+    "use_quant_conv",
+    "latents_std",
     "use_post_quant_conv",
-    "latents_std"
+    "latents_mean"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_006ebbe04966f503c7ba/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd06927024eb773d727111280344efa6bef7647c251e27684d7e32aac3a82428
+oid sha256:d29f5a02a4aed8154224ef378fd971199c6334429c49ac0fce3c10b5a6aa25b6
 size 370909427

neuronxcc-2.19.8089.0+8ab9f450/MODULE_006ebbe04966f503c7ba/vae_encoder/config.json

@@ -2,12 +2,12 @@
   "_class_name": "AutoencoderKL",
   "_diffusers_version": "0.35.1",
   "_use_default_values": [
-    "use_quant_conv",
     "mid_block_add_attention",
     "shift_factor",
-    "latents_mean",
+    "use_quant_conv",
+    "latents_std",
     "use_post_quant_conv",
-    "latents_std"
+    "latents_mean"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_006ebbe04966f503c7ba/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6ec863faa78d055e49edecdff2ef00d32f173a4872df90a9ee4e81b7f8619af
+oid sha256:36b97298d348c0a970653488fcc0b3759a93be90547422d756522da73fd25552
 size 222984881