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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Docs] Add ERNIE 4.5 to batch invariance tested models
- [Bug]: Elastic EP scale up crashes with EAGLE3 when CUDA graphs are on
- [Bugfix][Elastic EP] Reset the drafter compile wrapper when releasing CUDA graphs
- [Bugfix][EngineCore] Handle malformed ADD frames and input thread failures
- [Attention][SM120] Occupancy-adaptive Triton split-K segment count
- [Bugfix][EPD] Skip sampling for encoder-only async steps
- [Bugfix][Attention] Resolve kernel block-size constraints per layer head size
- [Bug]: verbose_json crashes when a Whisper chunk emits only EOS
- [Kernel][Perf] Add TP=2/4/8 per-rank shapes to the sm_120 batch-invariant matmul table
- [CI] Run DFlash2 NVFP4 acceptance test on B200; skip it on H200 35GB MIG
- Docs
- Python not yet supported