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
Yi_lmdeploy
Commits
f2d9d074
Commit
f2d9d074
authored
Jan 31, 2024
by
zhouxiang
Browse files
更新lmdeploy到0.1.0版本
parent
14c3b38d
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
8 additions
and
6 deletions
+8
-6
.gitmodules
.gitmodules
+1
-1
README.md
README.md
+6
-4
lmdeploy
lmdeploy
+1
-1
No files found.
.gitmodules
View file @
f2d9d074
[submodule "lmdeploy"]
path = lmdeploy
url = http://developer.hpccube.com/codes/aicomponent/lmdeploy.git
branch = dtk23.10-v0.
0.13-qwen
branch = dtk23.10-v0.
1.0
README.md
View file @
f2d9d074
...
...
@@ -18,10 +18,10 @@ Yi 系列模型以双语语言模型为目标,并在 3T 多语言语料库上
提供光源拉取推理的docker镜像:
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:lmdeploy-dtk23.10-torch1.13-py38
docker pull image.sourcefind.cn:5000/dcu/admin/base/custom:lmdeploy
1.0
-dtk23.10-torch1.13-py38
-latest
# <Host Path>主机端路径
# <Container Path>容器映射路径
docker run -it --name codellama --shm-size=1024G -v /opt/hyhal:/opt/hyhal --device=/dev/kfd --device=/dev/dri/ --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ulimit memlock=-1:-1 --ipc=host --network host --group-add video -v <Host Path>:<Container Path> image.sourcefind.cn:5000/dcu/admin/base/custom:lmdeploy-dtk23.10-torch1.13-py38 /bin/bash
docker run -it --name codellama --shm-size=1024G -v /opt/hyhal:/opt/hyhal --device=/dev/kfd --device=/dev/dri/ --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ulimit memlock=-1:-1 --ipc=host --network host --group-add video -v <Host Path>:<Container Path> image.sourcefind.cn:5000/dcu/admin/base/custom:lmdeploy
1.0
-dtk23.10-torch1.13-py38
-latest
/bin/bash
```
## 数据集
无
...
...
@@ -30,6 +30,8 @@ docker run -it --name codellama --shm-size=1024G -v /opt/hyhal:/opt/hyhal --devi
### 源码编译安装
```
# 若使用光源的镜像,可以不用源码编译,镜像里面安装好了lmdeploy,可跳过源码编译安装
# 获取源码,编译并安装
git clone http://developer.hpccube.com/codes/modelzoo/yi_lmdeploy.git
cd yi_lmdeploy
git submodule init && git submodule update
...
...
@@ -74,7 +76,7 @@ lmdeploy serve gradio --model_path_or_server ./workspace_yi-34b --server_name {s
```
shell
# --instance_num: turbomind推理实例的个数。可理解为支持的最大并发数
# --tp: 在 tensor parallel时,使用的GPU数量
lmdeploy serve api_server ./workspace_yi-34b
--server_name
${
server_ip
}
--server_port
${
server_port
}
--instance_num
32
--tp
4
lmdeploy serve api_server ./workspace_yi-34b
--server_name
${
server_ip
}
--server_port
${
server_port
}
--tp
4
```
浏览器上打开
`http://{server_ip}:{server_port}`
,即可访问 swagger,查阅 RESTful API 的详细信息。
...
...
@@ -92,7 +94,7 @@ lmdeploy serve gradio restful_api_url --server_name ${server_ip} --server_port $
```
**需要保证'{server_ip}:{server_port}'在外部浏览器中的可访问性**
关于 RESTful API的详细介绍,请参考
[
这份
](
https://developer.hpccube.com/codes/aicomponent/lmdeploy/-/blob/dtk23.0
4
-v0.
0.13
/docs/zh_cn/restful_api.md
)
文档。
关于 RESTful API的详细介绍,请参考
[
这份
](
https://developer.hpccube.com/codes/aicomponent/lmdeploy/-/blob/dtk23.
1
0-v0.
1.0
/docs/zh_cn/restful_api.md
)
文档。
## result

...
...
lmdeploy
@
d033914f
Subproject commit
206219aad30d88ad510287218f4fd17e22845
14
2
Subproject commit
d033914f0a2ba0724f7b08905bd1f18a0afe18
14
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