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
- [ROCm][MoE] Split AITER CK and Triton MXFP4 W4A16 into separate backends
- [Kernel] Move Marlin lock storage to WorkspaceManager
- No capability flag declares which KV-cache kinds may be peeked past a candidate boundary — each margin implementation excludes Mamba by hand
- [Helion] Require Helion for CUDA builds
- [CI] Add GSM8K accuracy test for amd/DeepSeek-V4-Flash-MXFP4
- [Bugfix] Pull runai_streamer non-tensor model files on every node
- [Kernel][Helion] Reset mutated inputs between benchmark repetitions
- [ROCm][Perf] Select wvSplitK only in measured-profitable gfx950 regions
- [ROCm][Perf] Fuse Kimi-K3 AttnRes with RMSNorm
- [Bugfix] Copy packed_modules_mapping onto the instance before mutating it
- Docs
- Python not yet supported