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][Qwen3VL] Add `torch.compile` support for Qwen3VL
- [RFC]: Fault-Tolerant Expert Parallelism
- [WIP] Add general correctness check script for vLLM endpoints
- [WIP] Rebase of https://github.com/vllm-project/vllm/pull/27134 to latest main
- [bugfix]: Fix the issue where unsupported response format types could cause the inference service to crash, enhancing the robustness of vLLM.
- [RFC]: Robust End-to-End CI/CD Regression Testing for Speculative Decoding
- C8
- [refactor] [mla]: independently passing q_nope & q_rope
- [Misc] allow pass in different load config for eagle draft model
- Add per request tracking of TTIT at RequestStateStats level
- Docs
- Python not yet supported