Synchronizing local compiler cache.

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.2.0.dev8/stable-diffusion/stabilityai/stable-diffusion-2-1/f41992c9042c864c8f94.json

@@ -0,0 +1,127 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "stabilityai/stable-diffusion-2-1",
+  "_task": null,
+  "text_encoder": {
+    "architectures": [
+      "CLIPTextModel"
+    ],
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1024,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": 16,
+    "num_hidden_layers": 23,
+    "vocab_size": 49408
+  },
+  "unet": {
+    "_class_name": "UNet2DConditionModel",
+    "act_fn": "silu",
+    "addition_embed_type": null,
+    "addition_embed_type_num_heads": 64,
+    "addition_time_embed_dim": null,
+    "attention_head_dim": [
+      5,
+      10,
+      20,
+      20
+    ],
+    "attention_type": "default",
+    "block_out_channels": [
+      320,
+      640,
+      1280,
+      1280
+    ],
+    "center_input_sample": false,
+    "class_embed_type": null,
+    "class_embeddings_concat": false,
+    "conv_in_kernel": 3,
+    "conv_out_kernel": 3,
+    "cross_attention_dim": 1024,
+    "cross_attention_norm": null,
+    "down_block_types": [
+      "CrossAttnDownBlock2D",
+      "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": "2.17.194.0+d312836f",
+      "dynamic_batch_size": false,
+      "inline_weights_to_neff": false,
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_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": null,
+    "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,
+    "up_block_types": [
+      "UpBlock2D",
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D"
+    ],
+    "upcast_attention": true,
+    "use_linear_projection": true
+  }
+}

neuronxcc-2.17.194.0+d312836f/MODULE_f41992c9042c864c8f94/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7068841d5d170a9a274c5fcfc4bc67ef2c2493c71898ceefd23ca2044d67dea1
+oid sha256:1c64bf26338343c0c7e8abb7c89444e931783046a51b64330c7de181aeec5db0
 size 1372305465

neuronxcc-2.17.194.0+d312836f/MODULE_f41992c9042c864c8f94/unet/config.json

@@ -3,32 +3,32 @@
   "_commit_hash": null,
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
-    "conv_out_kernel",
-    "addition_embed_type_num_heads",
-    "dropout",
-    "projection_class_embeddings_input_dim",
-    "time_embedding_dim",
-    "time_embedding_type",
+    "encoder_hid_dim",
+    "time_cond_proj_dim",
     "time_embedding_act_fn",
+    "attention_type",
+    "num_attention_heads",
+    "resnet_out_scale_factor",
     "addition_embed_type",
+    "dropout",
+    "encoder_hid_dim_type",
     "mid_block_type",
-    "class_embed_type",
-    "resnet_out_scale_factor",
-    "conv_in_kernel",
-    "class_embeddings_concat",
-    "mid_block_only_cross_attention",
     "resnet_skip_time_act",
-    "addition_time_embed_dim",
-    "encoder_hid_dim_type",
-    "attention_type",
-    "transformer_layers_per_block",
+    "projection_class_embeddings_input_dim",
     "reverse_transformer_layers_per_block",
-    "timestep_post_act",
-    "time_cond_proj_dim",
+    "conv_in_kernel",
+    "conv_out_kernel",
+    "time_embedding_type",
+    "cross_attention_norm",
+    "addition_embed_type_num_heads",
+    "time_embedding_dim",
+    "class_embed_type",
+    "mid_block_only_cross_attention",
     "resnet_time_scale_shift",
-    "num_attention_heads",
-    "encoder_hid_dim",
-    "cross_attention_norm"
+    "class_embeddings_concat",
+    "timestep_post_act",
+    "addition_time_embed_dim",
+    "transformer_layers_per_block"
   ],
   "act_fn": "silu",
   "addition_embed_type": null,

neuronxcc-2.17.194.0+d312836f/MODULE_f41992c9042c864c8f94/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f366219a8e19c0d1f01c285796a6c0daa2d8897ec5bf7996a5abb3864aa12b
+oid sha256:cb9f5b5db20bf89d5e2a835a18bbf3019849ac4a3f3f09cd7e050ba01e42a676
 size 3767181069

neuronxcc-2.17.194.0+d312836f/MODULE_f41992c9042c864c8f94/vae_decoder/config.json

@@ -4,12 +4,12 @@
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
     "latents_mean",
-    "use_post_quant_conv",
-    "use_quant_conv",
-    "force_upcast",
-    "scaling_factor",
     "latents_std",
+    "scaling_factor",
     "mid_block_add_attention",
+    "force_upcast",
+    "use_post_quant_conv",
+    "use_quant_conv",
     "shift_factor"
   ],
   "act_fn": "silu",

neuronxcc-2.17.194.0+d312836f/MODULE_f41992c9042c864c8f94/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:838b55d023afc484cce44b2f900cfa1627176e6e4a6c88802624a31e716276bd
+oid sha256:de54645a49f9ec683756f853127b8053b3e31971a14f703511c8cb2f37e59573
 size 600343701

neuronxcc-2.17.194.0+d312836f/MODULE_f41992c9042c864c8f94/vae_encoder/config.json

@@ -4,12 +4,12 @@
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
     "latents_mean",
-    "use_post_quant_conv",
-    "use_quant_conv",
-    "force_upcast",
-    "scaling_factor",
     "latents_std",
+    "scaling_factor",
     "mid_block_add_attention",
+    "force_upcast",
+    "use_post_quant_conv",
+    "use_quant_conv",
     "shift_factor"
   ],
   "act_fn": "silu",

neuronxcc-2.17.194.0+d312836f/MODULE_f41992c9042c864c8f94/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576f49d0604bba10d35b6cdc54a57644678fcb2f971aac74c4452af949fde150
+oid sha256:b1a073b6b86680bfd0e620762b8864b6896be327555090a12272ee4f88b991c3
 size 351604243