microsoft / microsoft/MInference
[Question]: Setup with VLLM
Open
@iofu728 is already working on this.
Since Aug 4, 2025.
question
- Dominant language
- Python
- Stars
- 1.2k
- Forks
- 82
- Avg merge
- 1d 18h
- Merged PRs (30d)
- 1
Description
Describe the issue
I am trying to install Minference and vLLM simultaneously, but encountered a version conflict.
The installation guide specifies the following steps:
uv pip install "vllm>=0.9.0"
uv pip install git+https://github.com/vllm-project/flash-attention
Here, the installed flash-attn version is vllm-flash-attn 2.7.2.post1+cu128.
However, this version of flash-attn requires PyTorch 2.4.0, which conflicts with vLLM ≥ 0.9.0's requirement of PyTorch 2.7.0.
Could you clarify the exact versions I should use to resolve this conflict?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.