Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in
Toggle navigation
Menu
Open sidebar
ModelZoo
Qwen3.5
Commits
f9220158
Commit
f9220158
authored
Mar 12, 2026
by
weishb
Browse files
support 8w8a model
parent
618b21ce
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
5 additions
and
2 deletions
+5
-2
README.md
README.md
+5
-2
vllm-0.15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
....15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
+0
-0
No files found.
README.md
View file @
f9220158
...
@@ -46,7 +46,9 @@ docker run -it \
...
@@ -46,7 +46,9 @@ docker run -it \
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,numpy、transformers库需要替换安装:
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,numpy、transformers库需要替换安装:
```
```
pip install git+https://github.com/huggingface/transformers.git
pip uninstall vllm
pip install vllm-0.15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
pip install transformers==5.2.0
pip install numpy==1.25.0
pip install numpy==1.25.0
```
```
...
@@ -60,7 +62,7 @@ pip install numpy==1.25.0
...
@@ -60,7 +62,7 @@ pip install numpy==1.25.0
### vllm
### vllm
#### 单机推理
#### 单机推理
**注意**
:使用
`K100 AI`
启动服务时需要添加
`--disable-custom-all-reduce`
参数
**注意**
:使用
`K100 AI`
启动服务时需要添加
`--disable-custom-all-reduce`
参数
,加载8W8A模型启动服务时需要添加
`-cc.mode=3`
和
`-cc.inductor_compile_config='{"combo_kernels": false, "benchmark_combo_kernel": false}'`
```
bash
```
bash
## serve启动
## serve启动
...
@@ -174,6 +176,7 @@ DCU与GPU精度一致,推理框架:vllm。
...
@@ -174,6 +176,7 @@ DCU与GPU精度一致,推理框架:vllm。
| 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 |
|:------:|:----:|:----------:|:------:|:---------------------:|
|:------:|:----:|:----------:|:------:|:---------------------:|
| Qwen3.5-397B-A17B | 397B | K100AI,BW1000 | 16 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-397B-A17B
)
|
| Qwen3.5-397B-A17B | 397B | K100AI,BW1000 | 16 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-397B-A17B
)
|
| Qwen3.5-397B-A17B | 397B | K100AI,BW1000 | 8 |
[
Modelscope
](
https://www.modelscope.cn/models/metax-tech/Qwen3.5-397B-A17B-W8A8
)
|
| Qwen3.5-122B-A10B | 122B | K100AI,BW1000 | 8 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-122B-A10B
)
|
| Qwen3.5-122B-A10B | 122B | K100AI,BW1000 | 8 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-122B-A10B
)
|
| Qwen3.5-35B-A3B | 35B | K100AI,BW1000 | 2 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-35B-A3B
)
|
| Qwen3.5-35B-A3B | 35B | K100AI,BW1000 | 2 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-35B-A3B
)
|
| Qwen3.5-27B | 27B | K100AI,BW1000 | 2 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-27B
)
|
| Qwen3.5-27B | 27B | K100AI,BW1000 | 2 |
[
Hugging Face
](
https://huggingface.co/Qwen/Qwen3.5-27B
)
|
...
...
vllm-0.15.1+das.opt1.alpha.dtk2604-cp310-cp310-linux_x86_64.whl
0 → 100644
View file @
f9220158
File added
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