vllm-project / vllm-metal
Community maintained hardware plugin for vLLM on Apple Silicon
Why this job: topics: apple-silicon, vllm, mlx
What it does
Upstream vLLM supplies the API server, scheduler, and paged block manager; mlx_lm supplies the token-wise model layers; vllm-metal owns the request-aware attention path — the paged varlen kernel, M5 NAX prefill, and speculative decoding.
Get started
brew tap vllm-project/vllm-metal https://github.com/vllm-project/vllm-metal
brew install vllm-project/vllm-metal/vllm-metal You need: macOS 15 (Sequoia) or later, on Apple Silicon
- Maintenance
- Active
- Last commit today
- Stars
- 1,974
- +32 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- Mac
- From the latest release
- Latest version
- v0.33.0
- Released 5 days ago
- Built with
- Python
- 91% of the code
Is it looked after?
- Contributors
- 28
- Last 90 days
- Issues
- 90% closed
- 22 still open
- Pull requests
- 852 merged
- 46 waiting
- Releases
- 9
- 9 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| jundot / omlx | 23,475 | 4 days ago | Apache-2.0 | Mac |
| incoai / splash | 2,159 | 3 days ago | Apache-2.0 | Mac |
| Neywa-Labs / nativ | 1,581 | today | MIT | Mac |
More: download files, languages, topics and project record
Languages
- Python 91%
- Metal 5%
- C++ 3%
- Shell <1%
Topics
- apple-silicon
- llm
- macos
- metal
- mlx
- vllm
Project record
- JobLocal LLMs
- StatusFeatured
- Commits965
- Forks346
- Watching9
- Stars in 28 days+127
- CreatedDec 12, 2025
- First seen by usNov 7, 2026
- CheckedNov 9, 2026