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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][Reasoning] Keep the closing delimiter when append-think meets the tool parser
- [Kernel] Avoid redundant SM100 blockwise FP8 scale padding
- [Bugfix][KV Events] Emit BlockRemoved only for the last cached copy of a block hash
- [Perf][CPU] Reduce AVX2 prefill attention register spills
- [Core] Bound async GPU output synchronization
- [Bugfix] Cover off-grid cudagraph capture sizes under an explicit maximum
- [Perf] Increase PDL overlap for Linear LoRA Shrink and Expand
- [Perf][DSA] Shard the decode indexer rows across TP ranks
- [RFC]: KV Context Editing — Relaxed Prefix Alignment for KV Allocation and Reuse
- [Security] Reject unresolved paths in Kimi vision loading
- Docs
- Python not yet supported