Update app.py

app.py

@@ -97,12 +97,7 @@ model = AutoModelForCausalLM.from_pretrained(
     attn_implementation="flash_attention_2",  # To enable flashattn, you have to install flash-attn
 ).to(device)
 model.eval()
-
-# Apply dynamic quantization
-model = torch.quantization.quantize_dynamic(
-    model, {torch.nn.Linear}, dtype=torch.qint8
-).to(device)
-model.eval()
+# gonna use either gguf or vllm later
 
 basic_model_config = './xcodec_mini_infer/final_ckpt/config.yaml'
 resume_path = './xcodec_mini_infer/final_ckpt/ckpt_00360000.pth'