Update README.md

README.md

@@ -22,8 +22,8 @@ pip download fastllm/Kimi-K2-Instruct-INT4MIX
 
 ``` sh
 # 假设模型下载在 /root/Kimi-K2-Instruct-INT4MIX
-pip run /root/Kimi-K2-Instruct-INT4MIX # 聊天模式
-pip server /root/Kimi-K2-Instruct-INT4MIX # API 服务器模式（默认模型名称 = /root/Kimi-K2-Instruct-INT4MIX，端口 = 8080）
+ftllm run /root/Kimi-K2-Instruct-INT4MIX # 聊天模式
+ftllm server /root/Kimi-K2-Instruct-INT4MIX # API 服务器模式（默认模型名称 = /root/Kimi-K2-Instruct-INT4MIX，端口 = 8080）
 ```
 
 # 优化
@@ -36,7 +36,7 @@ pip server /root/Kimi-K2-Instruct-INT4MIX # API 服务器模式（默认模型
 例如：
 
 ``` sh
-pip server /root/Kimi-K2-Instruct-INT4MIX -t 12
+ftllm server /root/Kimi-K2-Instruct-INT4MIX -t 12
 ```
 
 ## 多 CPU（多 NUMA 节点）
@@ -77,8 +77,8 @@ pip download fastllm/Kimi-K2-Instruct-INT4MIX
 
 ``` sh
 # Assuming the model is downloaded in /root/Kimi-K2-Instruct-INT4MIX
-pip run /root/Kimi-K2-Instruct-INT4MIX # chat
-pip server /root/Kimi-K2-Instruct-INT4MIX # api server (default model_name = /root/Kimi-K2-Instruct-INT4MIX, port = 8080)
+ftllm run /root/Kimi-K2-Instruct-INT4MIX # chat
+ftllm server /root/Kimi-K2-Instruct-INT4MIX # api server (default model_name = /root/Kimi-K2-Instruct-INT4MIX, port = 8080)
 ```
 
 # optimize
@@ -91,7 +91,7 @@ If the speed is extremely slow, it may be due to too many threads—consider red
 for example:
 
 ``` sh
-pip server /root/Kimi-K2-Instruct-INT4MIX -t 12
+ftllm server /root/Kimi-K2-Instruct-INT4MIX -t 12
 ```
 
 ## multi cpu (multi numa node)