Update app.py

app.py

@@ -2,12 +2,10 @@ import gradio as gr
 import os, gc, copy, torch, re
 from datetime import datetime
 from huggingface_hub import hf_hub_download
-from pynvml import *
-nvmlInit()
-gpu_h = nvmlDeviceGetHandleByIndex(0)
+
 ctx_limit = 512
 title = "RWKV-4-World-0.4B-v1-20230529-ctx4096"
-os.environ["RWKV_JIT_ON"] = '0'
+os.environ["RWKV_JIT_ON"] = '1'
 os.environ["RWKV_CUDA_ON"] = '0' # if '1' then use CUDA kernel for seq mode (much faster)
 
 from rwkv.model import RWKV