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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Kernel] ReplaySSM: cache SSM inputs for faster Mamba2 speculative decode
- [Bug]: EngineDeadError NVFP4 marlin
- fix: Add fp8 einsum warmup
- [Bugfix] Fix ModelOpt NVFP4 TP shard alignment
- [Regression] Trailing <turn|> token appearing at the end of generated text in vLLM 0.26.0
- [Perf] DSD arms pay a large baseline tax vs no-spec under production defaults; PIECEWISE override identified as one factor
- [Bug]: Multimodal models fail to load on ROCm/RDNA4 (gfx1201) — `CUDA error: invalid argument` in `vit_torch_sdpa_wrapper` encoder attention
- [Bugfix][Quantization] Match draft model quant targets under its root prefix
- [Perf] #48137 costs ~10.6% spec-decode acceptance and #48660 shifts output distributions on DeepSeek-V4-Flash — isolated via #48660-only arm on a production 2-node deployment
- [Bugfix][Kernel] Keep DeepGEMM FP8 quant inside opaque op for TMA scales
- Docs
- Python not yet supported