Skip to content

GitLab

Commit d403d2ad authored by luopl's avatar luopl
Browse files

Update README.md

parent 82184857
Hide whitespace changes
Inline Side-by-side
Showing with 5 additions and 5 deletions
README.md
View file @ d403d2ad
...@@ -26,7 +26,7 @@ Step-Video-T2 V是一种使用流匹配训练的基于扩散Transformer（DiT） ...@@ -26,7 +26,7 @@ Step-Video-T2 V是一种使用流匹配训练的基于扩散Transformer（DiT）
### Docker（方法一） ### Docker（方法一）
``` ```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.3.0-ubuntu22.04-dtk24.04.3-py3.10 docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.4.1-ubuntu22.04-dtk25.04-py3.10-fixpy
# <your IMAGE ID>为以上拉取的docker的镜像ID替换 # <your IMAGE ID>为以上拉取的docker的镜像ID替换
docker run -it --name T2V_test --shm-size=1024G --device=/dev/kfd --device=/dev/dri/ --privileged --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ulimit memlock=-1:-1 --ipc=host --network host --group-add video -v /opt/hyhal:/opt/hyhal:ro -v $PWD/Step-Video-TI2V_pytorch:/home/Step-Video-T2V_pytorch <your IMAGE ID> /bin/bash docker run -it --name T2V_test --shm-size=1024G --device=/dev/kfd --device=/dev/dri/ --privileged --cap-add=SYS_PTRACE --security-opt seccomp=unconfined --ulimit memlock=-1:-1 --ipc=host --network host --group-add video -v /opt/hyhal:/opt/hyhal:ro -v $PWD/Step-Video-TI2V_pytorch:/home/Step-Video-T2V_pytorch <your IMAGE ID> /bin/bash
cd /home/Step-Video-T2V_pytorch cd /home/Step-Video-T2V_pytorch
...@@ -48,11 +48,11 @@ sh fix.sh ...@@ -48,11 +48,11 @@ sh fix.sh
1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装： 1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装：
- https://developer.hpccube.com/tool/ - https://developer.hpccube.com/tool/
``` ```
DTK驱动:dtk24.04.3 DTK驱动:dtk25.04
python:python3.10 python:python3.10
torch:2.3.0 torch:2.4.1
torchvision:0.18.1 torchvision:0.19.1
triton:2.1.0 triton:3.0.0
flash-attn:2.6.1 flash-attn:2.6.1
``` ```
......
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