attempt compilation

app.py

@@ -7,11 +7,24 @@ import spaces
 
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
+torch.set_float32_matmul_precision("high")
+
+torch._inductor.config.conv_1x1_as_mm = True
+torch._inductor.config.coordinate_descent_tuning = True
+torch._inductor.config.epilogue_fusion = False
+torch._inductor.config.coordinate_descent_check_all_directions = True
+
 pipe = AuraFlowPipeline.from_pretrained(
 	"AuraDiffusion/AuraFlow",
     torch_dtype=torch.float16
 ).to("cuda")
 
+pipe.transformer.to(memory_format=torch.channels_last)
+pipe.vae.to(memory_format=torch.channels_last)
+
+pipe.transformer = torch.compile(pipe.transformer, mode="max-autotune", fullgraph=True)
+pipe.vae.decode = torch.compile(pipe.vae.decode, mode="max-autotune", fullgraph=True)
+
 MAX_SEED = np.iinfo(np.int32).max
 MAX_IMAGE_SIZE = 1024