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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- add fused mhc_post_pre kernel
- [RFC] Universal Translator: TP topology flexibility framework (Phase 1: ConstraintGroupedNorm + Ling pilot)
- [ROCm][CI] Avoid duplicate ROCm AITER norm-quant patterns
- Add metadata support to latency and throughput benchmarks
- [Build] Build bundled DeepGEMM `_C` per-Python so the wheel imports on every CPython
- [Bug]: AttributeError: '_C' object has no attribute 'awq_dequantize' on Intel Arc B580 XPU (AWQ inference fails)
- [Refactor] Remove dead code in tests and parallel_state
- [Bug]: Triton MXFP4 MoE kernel uses .tile::scatter4 PTX (Hopper/SM10 only) — fails on SM 12.1 (GB10/DGX Spark); Marlin fallback hits #37030
- [bug] Fix lora reloading from disk every step when using AsyncLLM
- [Bug]: Qwen3ForEmbedding no longer works
- Docs
- Python not yet supported