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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: NVFP4 MoE falls back to Marlin on sm_121 (GB10) in published builds, making the model unservable on a unified 121 GiB pool
- [Bugfix] Resolve $ref/$defs in tool schemas and preserve definitions
- perf: skip re-validating reused sampling params in streaming input loop
- [Bug]: Qwen parser routes grammar-constrained JSON to reasoning when `enable_in_reasoning=true`
- [Bug][Rocm] LMcache running issues for the kimik3 Dspark
- [Bugfix] Preserve the audio duration-limit error through the PyAV fallback
- [Perf][Multimodal] Downmix audio channels by slicing instead of reducing
- [Bug][ROCm] Remove `AITER_MXFP4_BF16` and `AITER_MXFP4_FP8` MOE routing hotfix once AITER is bumped
- [Frontend] Add Holo2 reasoning parser
- [Bugfix][Quantization] Fix dynamic INT8 W8A8 MoE config being built as W8A16
- Docs
- Python not yet supported