Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
ModelZoo
Baichuan-M3_pytorch
Commits
a293067a
Commit
a293067a
authored
Mar 06, 2026
by
shihm
Browse files
modified readme
parent
933b0e34
Changes
1
Show whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
12 additions
and
0 deletions
+12
-0
README.md
README.md
+12
-0
No files found.
README.md
View file @
a293067a
...
@@ -61,6 +61,18 @@ docker run -it \
...
@@ -61,6 +61,18 @@ docker run -it \
#### 多机推理
#### 多机推理
加入环境变量
加入环境变量
> 请注意:
> 每个节点上的环境变量都写到.sh文件中,保存后各个计算节点分别source`.sh`文件
>
> VLLM_HOST_IP:节点本地通信口ip,尽量选择IB网卡的IP,**避免出现rccl超时问题**
>
> NCCL_SOCKET_IFNAME和 GLOO_SOCKET_IFNAME:节点本地通信网口ip对应的名称
>
> 通信口和ip查询方法:ifconfig
>
> IB口状态查询:ibstat !!!一定要active激活状态才可用,各个节点要保持统一
```
bash
```
bash
export
ALLREDUCE_STREAM_WITH_COMPUTE
=
1
export
ALLREDUCE_STREAM_WITH_COMPUTE
=
1
export
VLLM_HOST_IP
=
x.x.x.x
# 对应计算节点的IP,选择IB口SOCKET_IFNAME对应IP地址
export
VLLM_HOST_IP
=
x.x.x.x
# 对应计算节点的IP,选择IB口SOCKET_IFNAME对应IP地址
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment