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]: LoRA linear path (lora_shrink/lora_expand) nondeterministic in serving; only an fp32-eager interior is stable — full elimination matrix
- [Bug] Kimi-K3: tool-call arguments don't stream — entire payload emitted in one SSE delta after minutes of silence
- [ROCm]: Bump torch 2.13, triton 3.8, torchaudio, torchvision
- [Nixl][PD] DCP support for MLA models
- [TPU] Exempt TPU from the V2 model runner PCP and Triton gates
- [Attention][MLA] Per-request scheduling for MLA chunked context
- [Bug]: DSpark spec decode dies in profile_run — forward_mqa warmup asserts topk_indices_buffer, which a drafter never has (regression from #50298)
- [ROCm][Bugfix] Fix wvSplitK OOB reads on strided activations
- [ROCm][Perf] Fix Kimi-K3 DSpark FP8 MLA verification
- [ROCm][MoE] Split AITER CK and Triton MXFP4 W4A16 into separate backends
- Docs
- Python not yet supported