update requirements.txt and llm_api.py

requirements.txt

@@ -2,7 +2,7 @@ langchain==0.0.237
 openai
 sentence_transformers
 chromadb
-fschat
+fschat==0.2.15
 transformers
 torch~=2.0.0
 fastapi~=0.99.1

server/llm_api.py

@@ -5,7 +5,6 @@ sys.path.append(os.path.dirname(os.path.dirname(__file__)))
 from configs.model_config import llm_model_dict, LLM_MODEL, LLM_DEVICE, LOG_PATH, logger
 import asyncio
 
-
 host_ip = "0.0.0.0"
 controller_port = 20001
 model_worker_port = 20002
@@ -67,18 +66,19 @@ def create_model_worker_app(
         act_order=None,
     )
     worker = ModelWorker(
-        controller_address,
-        worker_address,
-        worker_id,
-        no_register,
-        model_path,
-        model_names,
-        device,
-        num_gpus,
-        max_gpu_memory,
-        load_8bit,
-        cpu_offloading,
-        gptq_config,
+        controller_addr=controller_address,
+        worker_addr=worker_address,
+        worker_id=worker_id,
+        no_register=no_register,
+        model_path=model_path,
+        model_names=model_names,
+        device=device,
+        num_gpus=num_gpus,
+        max_gpu_memory=max_gpu_memory,
+        load_8bit=load_8bit,
+        cpu_offloading=cpu_offloading,
+        gptq_config=gptq_config,
+        # limit_worker_concurrency=1,
     )
     parser = argparse.ArgumentParser()
     args = parser.parse_args()
@@ -193,8 +193,7 @@ def run_openai_api(q):
 if __name__ == "__main__":
     logger.info(llm_model_dict[LLM_MODEL])
     model_path = llm_model_dict[LLM_MODEL]["local_model_path"]
-    model_path = "d:\\chatglm\\models\\chatglm-6b"
-
+    # model_path = "d:\\chatglm\\models\\chatglm-6b"
 
     logger.info(f"如需查看 llm_api 日志，请前往 {LOG_PATH}")
 
@@ -229,7 +228,6 @@ if __name__ == "__main__":
         model_worker_process.join()
         openai_api_process.join()
 
-
 # 服务启动后接口调用示例：
 # import openai
 # openai.api_key = "EMPTY" # Not support yet