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 supported51 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bug]: internlm loses tool calls when the opening marker is split across chunks
- fix: resolve Aria expert checkpoint loading failure
- [RFC]: Stateless Responses API in the Rust frontend
- [Bug][XPU]: LoRA initialization fails for W4A8 layer after XPU weight repacking
- [Bugfix][Tool Parser] Buffer partial opening marker across streaming chunks for InternLM2
- [Bugfix][KV Offload] Skip hashless sources at store completion
- [Bugfix][KV Offload] Fix private CPU buffer lifetime during shutdown
- [RFC][NIXL] Add graceful peer retirement example for UCX v1.22.x memory release
- [Bugfix][ROCm] Fix GPTQ half/half2 atomicAdd on ROCm 7.13 nightlies
- [Bugfix][XPU] Remove stale W4A8 weight after repacking
- Docs
- Python not yet supported