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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Doc] Update reasoning effort in DeepSeek-V4.1-Flash recipe
- fix extra check
- [Bugfix][Tokenizer] Honor generation controls in DeepSeek V3.2
- [Bugfix][MRV2] Use IEEE tl.div_rn for temperature and repetition-penalty division in Model Runner V2
- [Bug]: [CPU] DP×TP with explicit binds crashes with IndexError on 2-NUMA hosts
- [Bugfix][CPU] Name the cause when a DP rank's assigned NUMA nodes don't exist
- [LoRA] Add multi-CTA shrink
- [RFC]: Checkpoint-internal paging for hybrid recurrent state
- [KVOffload][P2P][CI] Add a fault slice to the P2P e2e matrix
- [Bugfix][XPU] Use int64 token index in the DeepSeek-V4 qnorm/RoPE kernel
- Docs
- Python not yet supported