Synchronizing local compiler cache.

neuronxcc-2.16.372.0+4a9b2326/0_REGISTRY/0.1.0/inference/stable-diffusion/stabilityai/stable-diffusion-xl-base-1.0/607af33578bfa3405f3a.json

@@ -0,0 +1 @@
+{"model_type": "stable-diffusion", "text_encoder": {"_attn_implementation_autoset": true, "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": "2.16.372.0+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": 12, "num_hidden_layers": 12, "output_hidden_states": true, "task": "feature-extraction", "vocab_size": 49408}, "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": [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": "2.16.372.0+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": 2816, "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": [1, 2, 10], "up_block_types": ["CrossAttnUpBlock2D", "CrossAttnUpBlock2D", "UpBlock2D"], "upcast_attention": null, "use_linear_projection": true}}

neuronxcc-2.16.372.0+4a9b2326/MODULE_607af33578bfa3405f3a/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bce50514498bfc96bf8b00c54369f91b7add4b974fcbaa40a9276a3dde607f12
+oid sha256:194741d1f2401e02b3d25cbedaced541a2d131460e2c76538e437c5b184c2767
 size 495981433

neuronxcc-2.16.372.0+4a9b2326/MODULE_607af33578bfa3405f3a/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a07904c333232f9e60984bb3afeee2ad0a473873b57ddb2cb5c9d0a65ebe06
+oid sha256:a6deeec0e7f69f2bb4676f233d31c5320f1c2ccb853cde82fc2290b16f57029c
 size 2800105963

neuronxcc-2.16.372.0+4a9b2326/MODULE_607af33578bfa3405f3a/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da5c867e8febdc987bf1188524faa4ae72dfae8d7186e7a7b798e19327ac830d
+oid sha256:9166a2c9807f05a6425daddc79c159048105c3111a36f92c9e931910aa291f86
 size 4172254589

neuronxcc-2.16.372.0+4a9b2326/MODULE_607af33578bfa3405f3a/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-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/vae",
   "_use_default_values": [
+    "use_quant_conv",
+    "mid_block_add_attention",
     "shift_factor",
     "use_post_quant_conv",
-    "mid_block_add_attention",
     "latents_mean",
-    "latents_std",
-    "use_quant_conv"
+    "latents_std"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.16.372.0+4a9b2326/MODULE_607af33578bfa3405f3a/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a8821013d88591a02de476a84f43108e9c31a71f340942b22e4bf0ce816cda
+oid sha256:0a1f3d618b1e6e37bbb04a2398c3534fcfb4f29a291a030cca572d75d24c579b
 size 619168307

neuronxcc-2.16.372.0+4a9b2326/MODULE_607af33578bfa3405f3a/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-base-1.0/snapshots/462165984030d82259a11f4367a4eed129e94a7b/vae",
   "_use_default_values": [
+    "use_quant_conv",
+    "mid_block_add_attention",
     "shift_factor",
     "use_post_quant_conv",
-    "mid_block_add_attention",
     "latents_mean",
-    "latents_std",
-    "use_quant_conv"
+    "latents_std"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.16.372.0+4a9b2326/MODULE_607af33578bfa3405f3a/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b116564acb3e5d46f0117c85f4efdbd267fc89ee0125dd879481c64f25d15a6
+oid sha256:dbb4f91c031da50e5ae9126850956beb386ee47100e5167087cf30a037e75b7a
 size 311323187