Synchronizing local compiler cache.

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0.dev2/inference/stable-diffusion/stabilityai/stable-diffusion-xl-refiner-1.0/350ee1ff99bd5e4b26d5.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder_2": {"_attn_implementation_autoset": true, "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": "2.16.372.0+4a9b2326", "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, "tensor_parallel_size": 1}, "num_attention_heads": 20, "num_hidden_layers": 32, "output_hidden_states": true, "task": "feature-extraction", "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": "2.16.372.0+4a9b2326", "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, "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": 2560, "resnet_out_scale_factor": 1.0, "resnet_skip_time_act": false, "resnet_time_scale_shift": "default", "reverse_transformer_layers_per_block": null, "task": "semantic-segmentation", "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-2.16.372.0+4a9b2326/MODULE_350ee1ff99bd5e4b26d5/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b6acced67acefe576517de6145518b36e0d02849744ae198f73a1cedf1927b
+oid sha256:ea873151ffa3d8db745ccc3087b344eddee8232dba1c0a97faa5d47d993d29f8
 size 2800105013

neuronxcc-2.16.372.0+4a9b2326/MODULE_350ee1ff99bd5e4b26d5/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df1f4063795307beebfd2c5500f16e827c62145fce6d5ad67310c8bd2bedc149
+oid sha256:b27176c95d5408a016b45206558ce081543f10db9189d5e37d8d1d72cd9647d6
 size 3683407225

neuronxcc-2.16.372.0+4a9b2326/MODULE_350ee1ff99bd5e4b26d5/vae_decoder/config.json

@@ -4,12 +4,12 @@
   "_diffusers_version": "0.30.3",
   "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-refiner-1.0/snapshots/5d4cfe854c9a9a87939ff3653551c2b3c99a4356/vae",
   "_use_default_values": [
-    "mid_block_add_attention",
+    "latents_mean",
+    "use_quant_conv",
     "shift_factor",
     "latents_std",
-    "use_quant_conv",
-    "use_post_quant_conv",
-    "latents_mean"
+    "mid_block_add_attention",
+    "use_post_quant_conv"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.16.372.0+4a9b2326/MODULE_350ee1ff99bd5e4b26d5/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0e5fd387278895e9bfa8554e3eab92d0304fd7bcd3885f0ce2307729ce95e4f
+oid sha256:3691c0302d148e91132eebde40a196cdd9c2a1ea7ef2cd97e97d1ea751eeb37e
 size 619168307

neuronxcc-2.16.372.0+4a9b2326/MODULE_350ee1ff99bd5e4b26d5/vae_encoder/config.json

@@ -4,12 +4,12 @@
   "_diffusers_version": "0.30.3",
   "_name_or_path": "/home/runner/.cache/huggingface/hub/models--stabilityai--stable-diffusion-xl-refiner-1.0/snapshots/5d4cfe854c9a9a87939ff3653551c2b3c99a4356/vae",
   "_use_default_values": [
-    "mid_block_add_attention",
+    "latents_mean",
+    "use_quant_conv",
     "shift_factor",
     "latents_std",
-    "use_quant_conv",
-    "use_post_quant_conv",
-    "latents_mean"
+    "mid_block_add_attention",
+    "use_post_quant_conv"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.16.372.0+4a9b2326/MODULE_350ee1ff99bd5e4b26d5/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29125ae2131d1591f2e5b85050f2702289934930e5d371dfd065d0b5df3e9698
+oid sha256:ab94062a22590738666c7ba807da0815156807256db139df46cd4a558d042b73
 size 311323185