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
- [Doc] Fix stale references in metrics, transcription, and spec decode docs
- [Perf] Compute MRV2 prompt logits only for scored prompt rows
- [Bug]: GLM-5.3-Flash with --mm-encoder-tp-mode data gives wrong image and video answers (images look mixed up), TP=2 on B200, v0.31.0
- [ROCm][Perf][DSV4] Keep one decoder-replay row on unfinished prefills on gfx942
- [Feature][Kernel] Triton autotune block fp8
- [ROCm][Perf] Request fp32 output from the AITER router GEMM (otype)
- [Feature][Kernel] Triton autotune fused MoE
- [Fix] Stop MRV2 prompt logprobs at the end of the prompt
- [ROCm][Perf][Kimi-K3] Specialized decode: verify steps of 17-32 rows
- [Bug]: v0.25.0 picks FlashInfer mnnvl allreduce when multicast bind fails, then crashes with illegal memory access (2x H100)
- Docs
- Python not yet supported