EngineX-Hygon/enginex-hygon-vl
5
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
zhousha
2025-11-26 18:39:06 +08:00
parent bdc99d3750
commit 26f5964f32
5 changed files with 58 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
README.md
View File

@@ -1,3 +1,14 @@
# enginex-hygon-vl
运行于【海光 DCU】系列算力卡的【视觉多模态理解】引擎，基于 transformer 架构，支持 MiniCPM-V、Gemma 3 等最新流行模型
运行于【海光 DCU】系列算力卡的【视觉多模态理解】引擎，基于 transformer 架构，支持 MiniCPM-V、Gemma 3 等最新流行模型
因具体模型之间的启动方式和具体镜像会有略微差别，请详细查看 `/enginex` 目录下各个支持模型的启动测试方式。
## 可支持模型列表
可在项目文件夹 `/enginex` 下查看具体可支持模型文件的运行方式。
支持模型列表：
- PaddlePaddle/PaddleOCR-VL
- deepseek-ai/DeepSeek-OCR
- Qwen/Qwen2.5-7B-instruct
- Qwen/Qwen2-VL-2B-Instruct

9
enginex/DeepSeek-OCR.md Normal file
View File

@@ -0,0 +1,9 @@
# 运行方式
```python
docker pull git.modelhub.org.cn:9443/enginex-hygon/vllm:0.8.5-ubuntu22.04-dtk25.04.1-rc5-das1.6-py3.10-20250724
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_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro {imageID} bash
cd /your_code_path/deepseek-ocr_pytorch
```

13
enginex/PaddleOCR-VL.md Normal file
View File

@@ -0,0 +1,13 @@
# 运行方式
```python
docker pull git.modelhub.org.cn:9443/enginex-hygon/vllm:0.9.2-ubuntu22.04-dtk25.04.2-py3.10
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_data/:/path/your_code_data/ -v /opt/hyhal/:/opt/hyhal/:ro image.sourcefind.cn:5000/dcu/admin/base/vllm:0.9.2-ubuntu22.04-dtk25.04.2-py3.10 bash
cd /your_code_path/paddleocr-vl_paddle
python -m pip install paddlepaddle-dcu==3.2.1 -i https://www.paddlepaddle.org.cn/packages/stable/dcu/
python -m pip install -U "paddleocr[doc-parser]"
python -m pip install https://paddle-whl.bj.bcebos.com/nightly/cu126/safetensors/safetensors-0.6.2.dev0-cp38-abi3-linux_x86_64.whl
pip install paddlex==3.3.9
```

12
enginex/Qwen2-VL-2B-Instruct.md Normal file
View File

@@ -0,0 +1,12 @@
# 运行方式
```python
docker pull git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.3.0-py3.10-dtk24.04.3-ubuntu20.04-vllm0.6
docker run -it --shm-size=1024G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name qwen2_vl_pytorch bash
cd /path/your_code_data/
pip install qwen-vl-utils[decord]
git clone git.modelhub.org.cn:9443/enginex-hygon/llama-factory.git
cd llama-factory
pip install -e ".[torch,metrics]"
pip install timm
```

12
enginex/Qwen2.5-7B-Instruct.md Normal file
View File

@@ -0,0 +1,12 @@
# 运行方式
```python
docker pull git.modelhub.org.cn:9443/enginex-hygon/git.modelhub.org.cn:9443/enginex-hygon/pytorch:2.1.0-ubuntu20.04-dtk24.04.2-py3.10
docker run -it --shm-size=1024G -v /path/your_code_data/:/path/your_code_data/ -v /opt/hyhal:/opt/hyhal --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name qwen2.5_72B_pytorch bash
cd /path/your_code_data/
cd LLaMA-Factory
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip install e . -i https://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
pip install deepspeed-0.12.3+gita724046.abi1.dtk2404.torch2.1.0-cp310-cp310-manylinux_2_31_x86_64.whl
```