vllm
https://github.com/vllm-project/vllm
Python
A high-throughput and memory-efficient inference and serving engine for LLMs
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Model] Add TranslateGemma support
- [BugFix] Fix AttributeError in MooncakeConnector logging for non-tensor KV caches
- [Performance]: Custom Helion Kernels
- [Perf] Overlap workspace_buffer.fill_(0) with compute in MLA attention
- [Bug]: Batch invariance fails on NVIDIA B200 (Blackwell) with torch.compile
- [Frontend] Add --disable-inference flag for GPU-free render-only deployments
- [MoE Refactor] DefaultMoERunner simplifcation
- [Feature]: Add environment variable support for configuring NIXL disaggregation backend
- [Bugfix][Hardware][AMD] Fix MXFP4 MoE backend selection for RDNA3 (gfx1100)
- [RFC]: Deprecate and delete InductorAdaptor in favor of InductorStandaloneAdaptor
- Docs
- Python not yet supported