Synchronizing local compiler cache.

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/stable-diffusion/stabilityai/stable-diffusion-xl-base-1.0/10594f969badb54b47e4.json

@@ -0,0 +1,170 @@
+{
+  "_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,
+    "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,
+    "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,
+    "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": 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-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db9e6600866163bc84d6187352578f715d610fc0e4762bfabb8bff5224c28e8e
+oid sha256:7dd9dcc61c8b9ccf528c5088dd9236c7ce208705dfec3b60a4618b4a8a08b53c
 size 496092729

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7d3b927e3da760a7d9f83c2be9dbcff6e2f892618252934336c4c7c78ccf6ce
+oid sha256:70518b1520863d543525eca958b9ede6ca911f77dc2f226e9618354d7dd8e0b1
 size 2801582571

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/unet/config.json

@@ -3,8 +3,8 @@
   "_commit_hash": null,
   "_diffusers_version": "0.34.0",
   "_use_default_values": [
-    "dropout",
     "attention_type",
+    "dropout",
     "reverse_transformer_layers_per_block"
   ],
   "act_fn": "silu",

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f268f0edc43c9c43ba4c0402d7fed357eea98741e8e655b45139faf6e5040a7b
+oid sha256:819ca3b0c5f76121c6214e1ea7b196ea8bb81bfafcd2eb96f4ac838aacfeb31c
 size 4157584957

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/vae_decoder/config.json

@@ -5,9 +5,9 @@
   "_use_default_values": [
     "use_post_quant_conv",
     "latents_std",
-    "latents_mean",
     "mid_block_add_attention",
     "use_quant_conv",
+    "latents_mean",
     "shift_factor"
   ],
   "act_fn": "silu",

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94bbe7d431169b30199929c9da43855078f1336ac5ea11a42c3040b4cc41f50d
+oid sha256:388dbec74558b3fa0eca9b28fc90d002f14603cff069d4c1ccfbf9b6d0cc05c3
 size 349015667

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/vae_encoder/config.json

@@ -5,9 +5,9 @@
   "_use_default_values": [
     "use_post_quant_conv",
     "latents_std",
-    "latents_mean",
     "mid_block_add_attention",
     "use_quant_conv",
+    "latents_mean",
     "shift_factor"
   ],
   "act_fn": "silu",

neuronxcc-2.19.8089.0+8ab9f450/MODULE_10594f969badb54b47e4/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45af1c009618518d25b3c5296b2169afa5307205d20f3bc4ade39c26b404dc5c
+oid sha256:26d66cc72b53e2b1719d345a9ff29ef9466ec05d50e02ecf1101b1e3169c1774
 size 201275507