Fixed model_worker generate_gate may blocked main thread (#2540) (#2562

)

fastchat/serve/base_model_worker.py

@@ -203,7 +203,7 @@ async def api_generate_stream(request: Request):
 async def api_generate(request: Request):
     params = await request.json()
     await acquire_worker_semaphore()
-    output = worker.generate_gate(params)
+    output = await asyncio.to_thread(worker.generate_gate, params)
     release_worker_semaphore()
     return JSONResponse(output)