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 supported30 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][NIXL] Fix best_of_n KV leak and early-notification race in P/D
- WIP: FP8 SSM Cache Checkpointing
- [Core][Spec Decode] Dynamic verification for dflash
- [Bugfix] Assert KV connector ext_tokens contract in scheduler
- manually fuse norm and rope
- [Performance]: Significant performance degradation v1/reranker under concurrent requests while swiching from v.0.19.1 to v0.20.2 v0.21.1
- [Performance]: V1 sample_tokens p99 can include sampled-output readiness; moving the wait to get_output did not improve serving throughput in my setup
- Revert "Add `model` to `WeightTransferEngine.__init__`" (#42922)
- [Feature]: Add supports to Intel/DeepSeek-V4-Pro-W4A16-AutoRound
- [Docs] Fix incorrect docstring for `all_non_structural_tag_constraints_none`
- Docs
- Python not yet supported