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 supported29 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature] Abort in-flight requests and drain outputs on shutdown
- [Frontend] Add srt and vtt response formats for audio transcription
- Revert "[Bugfix] ep_scatter kernel store-load race condition" (#34991)
- [refactor] Refactor SpeculativeConfig for speculative method extensibility
- [Test] Add unittests for CompilerManager
- [WIP][BugFix] Add missing shutdown() to LMCacheConnectorV1 to fix GPU failure on repeated model loading
- [BugFix][Core] zero out null kv block after cuda graph capture
- feat(riscv64): add RISC-V 64-bit pure-Python CPU support
- [Perf][Utility] Update RMSNorm benchmark script
- Fix/triton quant query input
- Docs
- Python not yet supported