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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- Fix Responses message store aliasing
- [Bugfix][Frontend] Abort realtime STT on disconnect; harden Anthropic tool JSON
- [Bug]: hybrid Mamba + `--mamba-cache-mode align`: a request near the KV-pool ceiling is admitted, prefilled to 98.9 %, requeued, and re-prefilled forever with zero output tokens and zero preemption accounting
- [Bugfix][Frontend] Keep vLLM MCP x-session-id over client headers
- [Build] Install infiniband-diags for DeepEP v2
- [Doc] Fix diagram rendering in GitHub Markdown
- [Bug]: Under async scheduling, stateful logits processors that read output_token_ids values see -1 placeholders — logitsprocs_need_output_token_ids only counts CLI custom processors
- [Bug]: qwen3_5_mtp fails to load at tensor-parallel-size >= 2 (drafter weight shape mismatch)
- [Bugfix] Fix --help=<keyword> state leaking between parse_args() calls
- [Bug]: Qwen 3.8 quark int4 loading failed.
- Docs
- Python not yet supported