Update server.py

server.py

@@ -3,7 +3,6 @@ from fastapi import Response
 import torch
 import time
 import litserve as ls
-from optimum.quanto import freeze, qfloat8, quantize
 from diffusers import FlowMatchEulerDiscreteScheduler, AutoencoderKL
 from diffusers.models.transformers.transformer_flux import FluxTransformer2DModel
 from diffusers.pipelines.flux.pipeline_flux import FluxPipeline
@@ -20,12 +19,6 @@ class FluxLitAPI(ls.LitAPI):
         vae = AutoencoderKL.from_pretrained("black-forest-labs/FLUX.1-schnell", subfolder="vae", torch_dtype=torch.bfloat16, revision="refs/pr/1")
         transformer = FluxTransformer2DModel.from_pretrained("black-forest-labs/FLUX.1-schnell", subfolder="transformer", torch_dtype=torch.bfloat16, revision="refs/pr/1")
 
-        # quantize to 8-bit to fit on an L4
-        quantize(transformer, weights=qfloat8)
-        freeze(transformer)
-        quantize(text_encoder_2, weights=qfloat8)
-        freeze(text_encoder_2)
-
         self.pipe = FluxPipeline(
             scheduler=scheduler,
             text_encoder=text_encoder,