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
- [Core][Kernel] Support dynamic activation scaling for ModelOpt NVFP4
- fix(kernel): restore scalar_t RMSNorm intermediate rounding boundary (#49616)
- add total start up time to the log
- [Bugfix] Fix HF benchmark datasets crashing when --hf-split is omitted
- p800 mrv2
- [Attention] Add experimental ZoomKV backend
- [Bug]: DFlash 推理效率异常
- [Bug]: ngram_gpu spec decode + structured outputs (xgrammar) + async scheduling: verifier accepts grammar-illegal draft tokens → "Failed to advance FSM", HTTP 500s and silent truncation under concurrency
- [Bug]: BatchPrefillWithPagedKVCache failed with error invalid argument
- [TurboQuant][TritonCPU] Enable triton-cpu path for Turbo-quant algorithm
- Docs
- Python not yet supported