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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [MoE][NVIDIA] Add shared expert fusion for TRTLLM FP8
- [CI][XPU] Prefix all Intel GPU CI step labels with "XPU" for dashboard visibility
- [Bugfix] Take the sliding window from the layer, not the KV cache group
- [CI/Release][1/N][XPU] Publish XPU Triton shim index
- [Bug][KV Offload] cudaHostRegister can leave mixed pinned/unpinned TP ranks
- [Bugfix][Core] Skip Mamba partial-tail stops after mid-block hits
- [Docs] Fix stale claim that Ray is the default multi-node runtime
- [FS-Offloading] : Simplify fs manager
- [Misc] Warn when EAGLE/MTP speculation costs a large prefix-cache hit
- [Attention][MLA] Fuse Kimi-K3 chunked-context K/V packing
- Docs
- Python not yet supported