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 supported48 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix][KV Cache] Fix incremental multimodal block hashing
- [Bugfix][Tool Parser] Fix xLAM streaming: duplicated arguments on finalize, markers leaking into content
- [Core] Distinguish reused from newly cached blocks in BlockStored
- [Bugfix][Tool Parser] GigaChat3: stop special tokens split across deltas leaking into output
- [Offloader] Prefetch weight offloading for large MoE models, plus a schedule planner
- [Bug]: ray DP backend at --data-parallel-size 1 discards the derived DP master IP and falls back to 127.0.0.1
- [Bugfix] Fall back to native sampler when FlashInfer sampling kernel fails to build
- [Observability] Add OpenTelemetry tracing to GPU-less render server endpoints
- [RFC]: Pluggable KV Cache Data Types
- [Bug][KV Offload] EAGLE volatile-tail boundary can collapse hybrid SWA replay to zero hits
- Docs
- Python not yet supported