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 supported25 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Fix gemma4 reasoning leak in multi-turn tool_choice=auto streaming (#39885)
- [Core] Replace routing replay with device cache and async D2H pipeline
- FlashInfer + DFlash + FP8 on RTX 4090
- [Prototype] Add Helion kernels as vLLM IR op implementations
- [REFACTOR][Triton] Per-token-head: first-chunk fast-path, mixed batch split, fused K+V, dedicated decode kernel
- [Quantization] Add TurboQuant online weight compression (Linear-only)
- [Don't Merge] Test CI with InstantTensor as default load format
- Gibberish with flashinfer_nvlink_two_sided on GB200/arm64
- [Core] Cache PostGradPassManager.uuid by compile_range
- [Feature]: Expose Word-Level Timestamps in `/v1/realtime` API for Voxtral Realtime
- Docs
- Python not yet supported