diff --git a/README.md b/README.md
index 554a747..7e3c7e5 100644
--- a/README.md
+++ b/README.md
@@ -17,6 +17,17 @@ ChatGLM-6B 使用了和 ChatGPT 相似的技术，针对中文问答和对话进
 
 **[2023/03/19]** 增加流式输出接口 `stream_chat`，已更新到网页版和命令行 Demo。修复输出中的中文标点。增加量化后的模型 [ChatGLM-6B-INT4](https://huggingface.co/THUDM/chatglm-6b-int4)
 
+
+## 友情链接
+以下是部分基于本仓库开发的开源项目：
+* [ChatGLM-MNN](https://github.com/wangzhaode/ChatGLM-MNN): 一个基于 MNN 的 ChatGLM-6B C++ 推理实现，支持根据显存大小自动分配计算任务给 GPU 和 CPU
+* [ChatGLM-Tuning](https://github.com/mymusise/ChatGLM-Tuning): 基于 LoRA 对 ChatGLM-6B 进行微调
+
+以下是部分针对本项目的教程/文档：
+* [Windows部署文档](https://github.com/ZhangErling/ChatGLM-6B/blob/main/deployment_windows.md)
+
+如果你有其他好的项目/教程的话，欢迎参照上述格式添加到README中并提出 [PR](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork).
+
 ## 使用方式
 
 ### 硬件需求
diff --git a/README_en.md b/README_en.md
index 3a8b17b..7b84f9c 100644
--- a/README_en.md
+++ b/README_en.md
@@ -13,6 +13,13 @@ Try the [online demo](https://huggingface.co/spaces/ysharma/ChatGLM-6b_Gradio_St
 
 **[2023/03/19]** Add streaming output function `stream_chat`, already applied in web and CLI demo. Fix Chinese punctuations in output. Add quantized model [ChatGLM-6B-INT4](https://huggingface.co/THUDM/chatglm-6b-int4). 
 
+## Projects
+The following are some open source projects developed based on this repository:
+* [ChatGLM-MNN](https://github.com/wangzhaode/ChatGLM-MNN): An [MNN](https://github.com/alibaba/MNN)-based implementation of ChatGLM-6B C++ inference, which supports automatic allocation of computing tasks to GPU and CPU according to the size of GPU memory
+* [ChatGLM-Tuning](https://github.com/mymusise/ChatGLM-Tuning): Fine-tuning ChatGLM-6B based on LoRA
+
+If you have other good projects, please refer to the above format to add to README and propose [PR](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request-from-a-fork).
+
 ## Getting Started
 
 ### Hardware Requirements
diff --git a/api.py b/api.py
index 10f70b6..693c70a 100644
--- a/api.py
+++ b/api.py
@@ -1,6 +1,19 @@
 from fastapi import FastAPI, Request
 from transformers import AutoTokenizer, AutoModel
 import uvicorn, json, datetime
+import torch
+
+DEVICE = "cuda"
+DEVICE_ID = "0"
+CUDA_DEVICE = f"{DEVICE}:{DEVICE_ID}" if DEVICE_ID else DEVICE
+
+
+def torch_gc():
+    if torch.cuda.is_available():
+        with torch.cuda.device(CUDA_DEVICE):
+            torch.cuda.empty_cache()
+            torch.cuda.ipc_collect()
+
 
 app = FastAPI()
 
@@ -13,7 +26,15 @@ async def create_item(request: Request):
     json_post_list = json.loads(json_post)
     prompt = json_post_list.get('prompt')
     history = json_post_list.get('history')
-    response, history = model.chat(tokenizer, prompt, history=history)
+    max_length = json_post_list.get('max_length')
+    top_p = json_post_list.get('top_p')
+    temperature = json_post_list.get('temperature')
+    response, history = model.chat(tokenizer,
+                                   prompt,
+                                   history=history,
+                                   max_length=max_length if max_length else 2048,
+                                   top_p=top_p if top_p else 0.7,
+                                   temperature=temperature if temperature else 0.95)
     now = datetime.datetime.now()
     time = now.strftime("%Y-%m-%d %H:%M:%S")
     answer = {
@@ -24,12 +45,12 @@ async def create_item(request: Request):
     }
     log = "[" + time + "] " + '", prompt:"' + prompt + '", response:"' + repr(response) + '"'
     print(log)
+    torch_gc()
     return answer
 
 
 if __name__ == '__main__':
-    uvicorn.run('api:app', host='0.0.0.0', port=8000, workers=1)
-
-tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
-model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
-model.eval()
+    tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
+    model = AutoModel.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True).half().cuda()
+    model.eval()
+    uvicorn.run(app, host='0.0.0.0', port=8000, workers=1)
diff --git a/cli_demo.py b/cli_demo.py
index 8a043fb..1c3ff2b 100644
--- a/cli_demo.py
+++ b/cli_demo.py
@@ -1,5 +1,6 @@
 import os
 import platform
+import signal
 from transformers import AutoTokenizer, AutoModel
 
 tokenizer = AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True)
@@ -8,6 +9,7 @@ model = model.eval()
 
 os_name = platform.system()
 clear_command = 'cls' if os_name == 'Windows' else 'clear'
+stop_stream = False
 
 
 def build_prompt(history):
@@ -18,8 +20,14 @@ def build_prompt(history):
     return prompt
 
 
+def signal_handler(signal, frame):
+    global stop_stream
+    stop_stream = True
+
+
 def main():
     history = []
+    global stop_stream
     print("欢迎使用 ChatGLM-6B 模型，输入内容即可进行对话，clear 清空对话历史，stop 终止程序")
     while True:
         query = input("\n用户：")
@@ -32,10 +40,15 @@ def main():
             continue
         count = 0
         for response, history in model.stream_chat(tokenizer, query, history=history):
-            count += 1
-            if count % 8 == 0:
-                os.system(clear_command)
-                print(build_prompt(history), flush=True)
+            if stop_stream:
+                stop_stream = False
+                break
+            else:
+                count += 1
+                if count % 8 == 0:
+                    os.system(clear_command)
+                    print(build_prompt(history), flush=True)
+                    signal.signal(signal.SIGINT, signal_handler)
         os.system(clear_command)
         print(build_prompt(history), flush=True)