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
- [Bugfix] Honor generation controls in the DeepSeek V4.1 tokenizer
- [Perf][DSv4.1] Speed up small Engram lookups
- [XPU] add weight_transfer test for XPU
- [Bugfix] Honor tokenizer revision in DeepSeek V4.1 Engram
- [Bugfix] Profile maximum DeepSeek V4.1 vision features
- fix(flashmla): bypass aten::new_empty int32 overflow during massive dummy runs
- Fix: Async EPLB silently drops batches during MoE offloading (Fixes #57883)
- [Docs][KV Cache] Clarify external cache reset semantics
- [Bugfix][Mamba] Preserve aligned prefix-cache snapshots with CoW
- [ROCm][PERF] Enable MiniMax-M3 Indexer CP
- Docs
- Python not yet supported