Delete app.py

app.py

@@ -1,39 +0,0 @@
-import torch
-import gradio as gr
-from diffusers import FluxPipeline
-from pruna import SmashConfig, smash
-
-# Load pipeline
-pipe = FluxPipeline.from_pretrained(
-    "black-forest-labs/FLUX.1-dev",
-    torch_dtype=torch.bfloat16
-).to("cuda")
-
-# Smash optimization
-smash_config = SmashConfig()
-smash_config["cacher"] = "fora"
-smash_config["fora_interval"] = 3  # or 2 for even faster inference
-smash_config["compiler"] = "torch_compile"
-smash_config["torch_compile_mode"] = "max-autotune-no-cudagraphs"
-smash_config["quantizer"] = "torchao"
-smash_config["torchao_quant_type"] = "int8dq"  # you can also try fp8dq
-smash_config["torchao_excluded_modules"] = "norm+embedding"
-
-smashed_pipe = smash(pipe, smash_config)
-
-# Inference function
-def generate_image(prompt: str):
-    image = smashed_pipe(prompt).images[0]
-    return image
-
-# Gradio UI
-demo = gr.Interface(
-    fn=generate_image,
-    inputs=gr.Textbox(label="Enter your prompt", placeholder="e.g. a knitted purple prune"),
-    outputs=gr.Image(label="Generated Image"),
-    title="FLUX.1-dev with Pruna Smash ⚡",
-    description="Optimized inference with Fora caching, Torch Compile, and TorchAO quantization."
-)
-
-if __name__ == "__main__":
-    demo.launch(share=True)