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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: Exllama GPTQ and RDNA3 W4A16 kernels silently produce wrong output when `group_size % 32 != 0` (reproduced on CUDA sm_120 and ROCm gfx1100)
- [Bugfix][Structured Output] Flag combinators with sibling constraints…
- [Bug]: FP8 KV cache startup can OOM because CUDA graph memory is omitted from the cache budget
- [ROCm] [Feat] Enable HiSparse on ROCm
- [Bug]: AOT-compiled artifact loading is decided per rank, so a partial load leaves ranks on different startup paths
- [Feature][Observability] Add production-ready Grafana dashboards
- [Bug]: Olmo3 tool parser corrupts string arguments with newlines and drops calls split across lines
- [BugFix] Keep newlines in Olmo3 tool-call arguments
- [Bug]: GLM-5.2-FP8 + prefix caching + FP8 KV cache returns empty content (gibberish reasoning) on repeated identical prompts
- [Bugfix] Preserve operator characters in sweep plot filter values
- Docs
- Python not yet supported