Synchronizing local compiler cache.

neuronxcc-2.19.8089.0+8ab9f450/0_REGISTRY/0.3.1.dev0/diffusion-transformer/Jingya/pixart_sigma_pipe_xl_2_512_ms/6b1e77a6020d68f9d72b.json

@@ -0,0 +1,100 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "Jingya/pixart_sigma_pipe_xl_2_512_ms",
+  "_task": null,
+  "text_encoder": {
+    "architectures": [
+      "T5EncoderModel"
+    ],
+    "classifier_dropout": 0.0,
+    "d_ff": 10240,
+    "d_kv": 64,
+    "d_model": 4096,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "dropout_rate": 0.1,
+    "export_model_type": "t5-encoder",
+    "feed_forward_proj": "gated-gelu",
+    "initializer_factor": 1.0,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "layer_norm_epsilon": 1e-06,
+    "model_type": "t5",
+    "neuron": {
+      "auto_cast": null,
+      "auto_cast_type": null,
+      "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": 120,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_decoder_layers": 24,
+    "num_heads": 64,
+    "num_layers": 24,
+    "output_past": true,
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "tie_word_embeddings": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "transformer": {
+    "_class_name": "PixArtTransformer2DModel",
+    "activation_fn": "gelu-approximate",
+    "attention_bias": true,
+    "attention_head_dim": 72,
+    "attention_type": "default",
+    "caption_channels": 4096,
+    "cross_attention_dim": 1152,
+    "double_self_attention": false,
+    "dropout": 0.0,
+    "in_channels": 4,
+    "interpolation_scale": 1,
+    "neuron": {
+      "auto_cast": null,
+      "auto_cast_type": null,
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.19.8089.0+8ab9f450",
+      "dynamic_batch_size": false,
+      "float_dtype": "bf16",
+      "inline_weights_to_neff": false,
+      "int_dtype": "int64",
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_encoder_hidden_size": 4096,
+      "static_height": 64,
+      "static_num_channels": 4,
+      "static_patch_size": 2,
+      "static_sequence_length": 120,
+      "static_vae_scale_factor": 8,
+      "static_width": 64,
+      "task": "semantic-segmentation",
+      "tensor_parallel_size": 1
+    },
+    "norm_elementwise_affine": false,
+    "norm_eps": 1e-06,
+    "norm_num_groups": 32,
+    "norm_type": "ada_norm_single",
+    "num_attention_heads": 16,
+    "num_embeds_ada_norm": 1000,
+    "num_layers": 28,
+    "num_vector_embeds": null,
+    "only_cross_attention": false,
+    "out_channels": 8,
+    "patch_size": 2,
+    "upcast_attention": false,
+    "use_additional_conditions": null,
+    "use_linear_projection": false
+  }
+}

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6b1e77a6020d68f9d72b/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3493d684d1c54c53f3855af6b761cdf20973e7fa3e38ea154c0753089b052b1
+oid sha256:bbfa363f7e1636b53400b437d9b348247ddf8a3fe34c16385759dad457cfa2a0
 size 9670751313

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6b1e77a6020d68f9d72b/transformer/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af909b232c11008233c7d7e3c37ac2ea8f47e0404d4b85072cbabb10d79a2867
+oid sha256:712a6b479bddee212cd34a2b4591ca984dfd044332c06c453ebea537838d89eb
 size 1290453084

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6b1e77a6020d68f9d72b/vae_decoder/config.json

@@ -3,12 +3,12 @@
   "_commit_hash": null,
   "_diffusers_version": "0.34.0",
   "_use_default_values": [
-    "shift_factor",
     "mid_block_add_attention",
-    "use_post_quant_conv",
-    "latents_std",
     "latents_mean",
-    "use_quant_conv"
+    "shift_factor",
+    "use_post_quant_conv",
+    "use_quant_conv",
+    "latents_std"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6b1e77a6020d68f9d72b/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6be93411b20be2cd7a4f5229d0820a03d81be7bea6b9c35f27694191e299e52
+oid sha256:a037c30d0e9c03bc6b57f858a12dab92fd4de0beb828981c7653f714302e884c
 size 152104149

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6b1e77a6020d68f9d72b/vae_encoder/config.json

@@ -3,12 +3,12 @@
   "_commit_hash": null,
   "_diffusers_version": "0.34.0",
   "_use_default_values": [
-    "shift_factor",
     "mid_block_add_attention",
-    "use_post_quant_conv",
-    "latents_std",
     "latents_mean",
-    "use_quant_conv"
+    "shift_factor",
+    "use_post_quant_conv",
+    "use_quant_conv",
+    "latents_std"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.19.8089.0+8ab9f450/MODULE_6b1e77a6020d68f9d72b/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a45454007d5acabc3f0f57f50fefa885f5d83c5cbf125d2a83485987c9b94d4
+oid sha256:23e7e1d609f62209cde3b2c4b6ab1403b34f76434ef5af84c34bf364e4702afc
 size 95453971