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 supported37 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Stream Kimi K3 tool-call arguments incrementally
- [Bug]: runai_streamer multi-node: aux (non-tensor) files are not pulled on peer nodes
- [Bugfix][Attention] Bound batch_size in GDN cudagraph padding branches
- [ROCm][MLA] Use asm decode for non-divisor small head counts
- [Bugfix] Fix MiniMax M3 prompt reasoning initialization
- [Feature]: SM8x (Ampere A100/A800) support for DeepSeek-V4-Flash / DeepSeek-V4-Flash-0731 DSpark
- [ROCm]Remove special-case SiTU support model-specific gating
- [ROCm][Perf] Fuse Kimi-K3 KDA decode gate
- [Bugfix][Model Runner V2] Preserve Mamba block table capacity under DCP
- [Model] Step3: guard tie_word_embeddings access for pipeline parallelism
- Docs
- Python not yet supported