Skip to content

Highlight RTX 50 CUDA 12.8 quick start #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
peter941221 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Highlight RTX 50 CUDA 12.8 quick start #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,8 @@ We provide pre-built Docker images that support out-of-the-box GPU inference env

### Quick Start

If you are using an RTX 50 series GPU, prefer the CUDA 12.8 image below. The repo's Docker docs already recommend CUDA 12.8 for RTX 50 series support.

```bash
# Pull pre-built image
docker pull modelbest-registry.cn-beijing.cr.aliyuncs.com/model-align/cpmcu_cu12.6:v1.0.0
Expand All @@ -89,6 +91,15 @@ docker run --gpus all -p 8000:8000 cpmcu:cuda12.6-release \
python examples/minicpm4/start_server.py --apply-sparse
```

```bash
# RTX 50 series quick start
docker pull modelbest-registry.cn-beijing.cr.aliyuncs.com/model-align/cpmcu_cu12.8:v1.0.0

docker tag modelbest-registry.cn-beijing.cr.aliyuncs.com/model-align/cpmcu_cu12.8:v1.0.0 cpmcu:cuda12.8-release

docker run --gpus all -it cpmcu:cuda12.8-release /bin/bash
```

### Offline Usage (Recommended)

```bash
Expand Down
11 changes: 11 additions & 0 deletions README_ZH.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -75,6 +75,8 @@ pip install .

### 快速开始

如果你使用的是 RTX 50 系显卡，建议优先使用下面的 CUDA 12.8 镜像。仓库现有 Docker 文档已经将 CUDA 12.8 作为 RTX 50 系支持的推荐路径。

```bash
# 拉取预构建镜像
docker pull modelbest-registry.cn-beijing.cr.aliyuncs.com/model-align/cpmcu_cu12.6:v1.0.0
Expand All @@ -89,6 +91,15 @@ docker run --gpus all -p 8000:8000 cpmcu:cuda12.6-release \
python examples/minicpm4/start_server.py --apply-sparse
```

```bash
# RTX 50 系快速开始
docker pull modelbest-registry.cn-beijing.cr.aliyuncs.com/model-align/cpmcu_cu12.8:v1.0.0

docker tag modelbest-registry.cn-beijing.cr.aliyuncs.com/model-align/cpmcu_cu12.8:v1.0.0 cpmcu:cuda12.8-release

docker run --gpus all -it cpmcu:cuda12.8-release /bin/bash
```

### 离线使用（推荐）

```bash
Expand Down