Skip to content

Add SDPA attention fallback and design docs #231

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
Lebhoryi wants to merge 3 commits into
base: main
Choose a base branch
from
Open

Add SDPA attention fallback and design docs #231

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d6e5659
fix(model): handle missing config dtype
Lebhoryi May 12, 2026
2d9b51b
feat(attention): add SDPA backend fallback
Lebhoryi May 12, 2026
d41fbe2
docs: add Nano-vLLM design docs
Lebhoryi May 12, 2026
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
10 changes: 10 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,6 +22,16 @@ A lightweight vLLM implementation built from scratch.
pip install git+https://github.com/GeeeekExplorer/nano-vllm.git
```

## Attention Backend

Nano-vLLM selects the attention backend automatically: it uses FlashAttention
when `flash-attn` is available, otherwise it falls back to PyTorch SDPA. You can
force a backend with the `NANOVLLM_ATTENTION_BACKEND` environment variable:

```bash
NANOVLLM_ATTENTION_BACKEND=sdpa python example.py
```

## Model Download

To download the model weights manually, use the following command:
Expand Down
Loading