增加停止服务的python脚本

server/llm_api_launch.py

@@ -1,5 +1,5 @@
 """
-调用示例: python llm_api_sh.py --model-path-address THUDM/chatglm2-6b@localhost@7650 THUDM/chatglm2-6b-32k@localhost@7651
+调用示例: python llm_api_launch.py --model-path-address THUDM/chatglm2-6b@localhost@7650 THUDM/chatglm2-6b-32k@localhost@7651
 其他fastchat.server.controller/worker/openai_api_server参数可按照fastchat文档调用
 但少数非关键参数如--worker-address,--allowed-origins,--allowed-methods,--allowed-headers不支持
 

server/llm_api_shutdown.py

@@ -0,0 +1,26 @@
+"""
+调用示例：
+python llm_api_shutdown.py --serve all
+可选"all","controller","worker","openai_api_server"， all表示停止所有服务
+"""
+import sys
+import os 
+sys.path.append(os.path.dirname(os.path.dirname(__file__)))
+
+import subprocess
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--serve",choices=["all","controller","worker","openai_api_server"])
+
+args = parser.parse_args()
+
+base_shell = "ps -eo user,pid,cmd|grep fastchat.serve{}|grep -v grep|awk '{print $2}'|xargs kill -9"
+
+if args.serve == "all":
+    shell_script = base_shell.format("")
+else:
+    serve = f".{args.serve}"
+    shell_script = base_shell.format(serve)
+
+subprocess.run(shell_script,shell=True,check=True)

server/setup_all.sh

@@ -1,30 +0,0 @@
-[ -d "../logs/" ] && echo "log dir exists" || mkdir "../logs/"
-# controller
-nohup python3 -m fastchat.serve.controller >../logs/controller.log 2>&1 &
-while [ `grep -c "Uvicorn running on" ../logs/controller.log` -eq '0' ];do
-        sleep 1s;
-        echo "wait controller running"
-done
-echo "controller running"
-
-# worker
-nohup python3 -m fastchat.serve.model_worker \
---model-name 'chatglm2-6b' \
---model-path THUDM/chatglm2-6b \
---num-gpus 2 \
->> ./logs/worker.log 2>&1 &
-
-while [ `grep -c "Uvicorn running on" ../logs/worker.log` -eq '0' ];do
-        sleep 3s;
-        echo "wait worker running"
-done
-echo "worker running"
-
-# webui
-nohup python3 -m fastchat.serve.openai_api_server >> "../logs/openai_server.log" 2>&1 &
-
-while [ `grep -c "Uvicorn running on" ../logs/openai_server.log` -eq '0' ];do
-        sleep 3s;
-        echo "wait openai_server running"
-done
-echo "openai_server running"

server/setup_controller.sh

@@ -1,7 +0,0 @@
-# controller
-nohup python3 -m fastchat.serve.controller >../logs/controller.log 2>&1 &
-while [ `grep -c "Uvicorn running on" ../logs/controller.log` -eq '0' ];do
-        sleep 1s;
-        echo "wait controller running"
-done
-echo "controller running"

server/setup_server.sh

@@ -1,8 +0,0 @@
-# webui
-nohup python3 -m fastchat.serve.openai_api_server >> "../logs/openai_server.log" 2>&1 &
-
-while [ `grep -c "Uvicorn running on" ../logs/openai_server.log` -eq '0' ];do
-        sleep 3s;
-        echo "wait openai_server running"
-done
-echo "openai_server running"

server/setup_worker.sh

@@ -1,11 +0,0 @@
-nohup python3 -m fastchat.serve.model_worker \
---model-name 'chatglm2-6b' \
---model-path THUDM/chatglm2-6b \
---num-gpus 2 \
->> ../logs/worker.log 2>&1 &
-
-while [ `grep -c "Uvicorn running on" ../logs/worker.log` -eq '0' ];do
-        sleep 3s;
-        echo "wait worker running"
-done
-echo "worker running"