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
Qwen3-VL_pytorch
Commits
87af59f9
Commit
87af59f9
authored
Jan 26, 2026
by
raojy
Browse files
updata
parent
52ee82b7
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
53 additions
and
12 deletions
+53
-12
README.md
README.md
+53
-12
doc/perform.png
doc/perform.png
+0
-0
No files found.
README.md
View file @
87af59f9
...
...
@@ -27,37 +27,41 @@ Visual Coding Boost:从图像/视频生成 Draw.io/HTML/CSS/JS。
3.
**Text–Timestamp Alignment:**
超越 T-RoPE,实现基于时间戳的精确事件定位,从而增强视频时间建模能力。
## 环境依赖
|
软件
| 版本
|
|:
--
----------:| :------: |
| DTK |
25.04.2
|
| python |
3.10.12
|
| transformers |
4.57.1
|
| torch | 2.5.1+das.opt1.dtk25042 |
| accelerate |
1.11.0
|
| 软件
| 版本
|
|
:----------:
| :------
----------------
: |
| DTK |
25.04.2
|
| python |
3.10.12
|
| transformers |
4.57.1
|
| torch | 2.5.1+das.opt1.dtk25042
|
| accelerate |
1.11.0
|
| torchvision | 0.20.1+das.opt1.dtk25042 |
|
flash_attn
| 2.6.1+das.opt1.dtk2504|
| av |
16.0.1
|
| flash_attn |
2.6.1+das.opt1.dtk2504
|
| av |
16.0.1
|
推荐使用镜像:
-
挂载地址
`-v`
,
`{docker_name}`
和
`{docker_image_name}`
根据实际模型情况修改
```
bash
docker run
-it
--shm-size
200g
--network
=
host
--name
{
docker_name
}
--privileged
--device
=
/dev/kfd
--device
=
/dev/dri
--device
=
/dev/mkfd
--group-add
video
--cap-add
=
SYS_PTRACE
--security-opt
seccomp
=
unconfined
-u
root
-v
/path/your_code_path/:/path/your_code_path/
-v
/opt/hyhal/:/opt/hyhal/:ro
{
docker_image_name
}
bash
示例如下:
docker pull
image
.sourcefind.cn:5
000
/dcu/admin/base/vllm:0.
9.2
-ubuntu22.04-dtk25.04.2-
py3.10
docker run
-it
--shm-size
200g
--network
=
host
--name
qwen3vl
--privileged
--device
=
/dev/kfd
--device
=
/dev/dri
--device
=
/dev/mkfd
--group-add
video
--cap-add
=
SYS_PTRACE
--security-opt
seccomp
=
unconfined
-u
root
-v
/path/your_code_path/:/path/your_code_path/
-v
/opt/hyhal/:/opt/hyhal/:ro
image
.sourcefind.cn:5
000
/dcu/admin/base/vllm:0.
9.2
-ubuntu22.04-dtk25.04.2-
py3.10
bash
docker pull
harbor
.sourcefind.cn:5
443
/dcu/admin/base/vllm:0.
11.0
-ubuntu22.04-dtk25.04.2-
1226-das1.7-py3.10-20251226
docker run
-it
--shm-size
200g
--network
=
host
--name
qwen3vl
--privileged
--device
=
/dev/kfd
--device
=
/dev/dri
--device
=
/dev/mkfd
--group-add
video
--cap-add
=
SYS_PTRACE
--security-opt
seccomp
=
unconfined
-u
root
-v
/path/your_code_path/:/path/your_code_path/
-v
/opt/hyhal/:/opt/hyhal/:ro
harbor
.sourcefind.cn:5
443
/dcu/admin/base/vllm:0.
11.0
-ubuntu22.04-dtk25.04.2-
1226-das1.7-py3.10-20251226
bash
#视频推理时安装PyAV后端依赖
pip
install
av
```
更多镜像可前往
[
光源
](
https://sourcefind.cn/#/service-list
)
下载使用。
关于本项目DCU显卡所需的特殊深度学习库可从
[
光合
](
https://developer.sourcefind.cn/tool/
)
开发者社区下载安装,其它包参照requirements.txt安装:
```
pip install -r requirements.txt
```
## 数据集
`暂无`
## 训练
...
...
@@ -120,9 +124,46 @@ Output:
<div
align=
center
>
<img
src=
"./doc/result_vedio.png"
/>
</div>
### vllm
#### 单机推理
```
bash
## serve启动
export
HF_HUB_OFFLINE
=
1
export
TRANSFORMERS_OFFLINE
=
1
vllm serve Qwen3-VL-8B-Instruct
\
--trust-remote-code
\
--max-model-len
32768
\
--served-model-name
qwen-vl
\
--dtype
bfloat16
\
--tensor-parallel-size
1
\
--gpu-memory-utilization
0.9
## client访问
curl http://localhost:8000/v1/chat/completions
\
-H
"Content-Type: application/json"
\
-d
'{
"model": "qwen-vl",
"messages": [
{
"role": "user",
"content": "牛顿提出了哪三大运动定律?请简要说明。"
}
]
}'
```
## vllm效果展示
<div
align=
center
>
<img
src=
"./doc/perform.png"
/>
</div>
### 精度
`DCU与GPU精度一致,推理框架:transformers。`
`DCU与GPU精度一致,支持推理框架:transformers、vllm。`
## 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|
...
...
doc/perform.png
0 → 100644
View file @
87af59f9
157 KB
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