Skip to content

Update vllm_deployment_guide.md for the AMD GPU support #32

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
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Update vllm_deployment_guide.md for the AMD GPU support #32

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
aff89a2
Update vllm_deployment_guide.md for the AMD GPU support
haic0 Sep 10, 2025
c6c7298
Update vllm_deployment_guide.md
haic0 Sep 13, 2025
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
30 changes: 30 additions & 0 deletions docs/vllm_deployment_guide.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -151,6 +151,36 @@ cd vllm/
pip install -e .
```

### AMD GPU Support
Copy link
Collaborator

@qscqesze qscqesze Sep 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It’s best to use ## AMD GPU Support; otherwise, this section will be considered part of the Common Issues chapter.


### Please follow the steps here to install and run LongCat-Flash-Chat models on AMD MI300X GPU.
Copy link
Collaborator

@qscqesze qscqesze Sep 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

What does LongCat-Flash-Chat refer to?（MeiTuan Model?) Could it be a typo in the model name?

Copy link
Author

@haic0 haic0 Sep 13, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Revised as MiniMax-M1, pls check, Thanks!

### Step By Step Guide
#### Step 1
Launch the Rocm-vllm docker:

```shell
docker pull rocm/vllm-dev:nightly

docker run -d -it --ipc=host --network=host --privileged --cap-add=CAP_SYS_ADMIN --device=/dev/kfd --device=/dev/dri --device=/dev/mem --group-add video --cap-add=SYS_PTRACE --security-opt seccomp=unconfined -v /:/work -e SHELL=/bin/bash --name vllm_minimax rocm/vllm-dev:nightly
```

#### Step 2
Huggingface login

```shell
huggingface-cli login
```


#### Step 3
Run the vllm online serving
Sample Command

```shell
SAFETENSORS_FAST_GPU=1 VLLM_USE_V1=0 vllm serve MiniMaxAI/MiniMax-M1-80k -tp 8 --gpu-memory-utilization 0.95 --no-enable-prefix-caching --trust-remote-code --max_model_len 4096 --dtype bfloat16
```


## 📮 Getting Support

If you encounter any issues while deploying MiniMax-M1 model:
Expand Down