Skip to content

GitLab

Commit 4bc377fc authored by shihm's avatar shihm
Browse files

updata readme

parent 79962e84
Show whitespace changes
Inline Side-by-side
Showing with 8 additions and 61 deletions
README.md
View file @ 4bc377fc
...@@ -94,69 +94,17 @@ print(response) ...@@ -94,69 +94,17 @@ print(response)
### vllm ### vllm
#### 多机推理 #### 单机推理
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
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 NCCL_SOCKET_IFNAME=ibxxxx
export GLOO_SOCKET_IFNAME=ibxxxx
export NCCL_IB_HCA=mlx5_0:1 # 环境中的IB网卡名字
unset NCCL_ALGO
export NCCL_MIN_NCHANNELS=16
export NCCL_MAX_NCHANNELS=16
export NCCL_NET_GDR_READ=1
export HIP_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
export VLLM_SPEC_DECODE_EAGER=1
export VLLM_MLA_DISABLE=0
export VLLM_USE_FLASH_MLA=1
export VLLM_RPC_TIMEOUT=1800000
# K100_AI集群建议额外设置的环境变量：
export VLLM_ENFORCE_EAGER_BS_THRESHOLD=44
# 海光CPU绑定核
export VLLM_NUMA_BIND=1
export VLLM_RANK0_NUMA=0
export VLLM_RANK1_NUMA=1
export VLLM_RANK2_NUMA=2
export VLLM_RANK3_NUMA=3
export VLLM_RANK4_NUMA=4
export VLLM_RANK5_NUMA=5
export VLLM_RANK6_NUMA=6
export VLLM_RANK7_NUMA=7
```
启动RAY集群
x.x.x.x对应第一步的head节点VLLM_HOST_IP
```bash
# head节点执行
ray start --head --node-ip-address=x.x.x.x --port=6379 --num-gpus=8 --num-cpus=32
# worker节点执行
ray start --address='x.x.x.x:6379' --num-gpus=8 --num-cpus=32
```
启动vllm server 启动vllm server
```bash ```bash
vllm serve /baichuan-inc/Baichuan-M3-235B vllm serve /baichuan-inc/Baichuan-M3-235B
--host x.x.x.x --port 8000 --reasoning-parser qwen3
--distributed-executor-backend ray --tensor-parallel-size 8
--tensor-parallel-size 16 --trust-remote-code
--gpu-memory-utilization 0.9 --port 8000
--gpu-memory-utilization 0.95
--served-model-name baichuan-m3 --served-model-name baichuan-m3
--reasoning-parser deepseek_r1
``` ```
启动完成后可通过以下方式访问： 启动完成后可通过以下方式访问：
```bash ```bash
...@@ -187,11 +135,10 @@ curl http://localhost:8000/v1/chat/completions \ ...@@ -187,11 +135,10 @@ curl http://localhost:8000/v1/chat/completions \
## 预训练权重 ## 预训练权重
| 模型名称 | 权重大小 | DCU型号 | 最低卡数需求 |下载地址| | 模型名称 | 权重大小 | DCU型号 | 最低卡数需求 |下载地址|
|:-----:|:----------:|:----------:|:---------------------:|:----------:| |:-----:|:----------:|:----------:|:---------------------:|:----------:|
| Baichuan-M3-235B | 235B | BW1000 | 16 | [Modelscope](https://modelscope.cn/models/baichuan-inc/Baichuan-M3-235B) | | Baichuan-M3-235B | 235B | BW1000 | 8 | [Modelscope](https://modelscope.cn/models/baichuan-inc/Baichuan-M3-235B) |
## 源码仓库及问题反馈 ## 源码仓库及问题反馈
- https://developer.sourcefind.cn/codes/modelzoo/baichuan-m3-235b_vllm - https://developer.sourcefind.cn/codes/modelzoo/baichuan-m3-235b_vllm
## 参考资料 ## 参考资料
- https://www.baichuan-ai.com/blog/baichuan-M3 - https://www.baichuan-ai.com/blog/baichuan-M3
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment