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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [DSV4][XPU] Pass gemm1_clamp_limit to XpuFusedMoe
- [ROCm][DSv3.2] Eliminate per-decode FillFunctor launches in sparse-MLA hot loop
- [Bug]: mistral w4a16 Quantization slower than FP16
- [Bug]: mooncake+PD混部,高并发preempt,偶发服务宕机,ValueError: Counters can only be incremented by non-negative amounts
- [Profiler] Support multiple profiling windows
- [Bug]: multimodal processor cache drops audio for use_audio_in_video, causing StopIteration / HTTP 400 (Qwen3-Omni)
- [Bugfix] Couple audio+video in mm processor cache for use_audio_in_video (fixes #44538)
- [ROCm][MLA] AITER FP8 ASM prefill backend
- [Bug]: GLM-5 FP8 OOM for long inputs at `flash_mla_cuda.sparse_decode_fwd` on H200
- [Feature] Add fault tolerance framework (simplified) for DP+EP external LB deployments
- Docs
- Python not yet supported