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 supported19 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [ROCm] Add cascade attention support for AITER FlashAttention backend
- [EPLB] Add nixl-based eplb communicator
- add testing for `Qwen3.5-27B-FP8` to GSM8K eval
- [BugFix] Download mmproj GGUF files for multimodal models in download…
- [Bugfix] Fix Qwen3-VL video embedding path (enable_mm_embeds)
- [Feature] Add /live liveness probe, LLM.shutdown(), and k8s shutdown docs
- [MoE Refactor] Migrate Unquantized to Full Oracle Flow
- [Hybrid][KVCache] Adjust alignment block size according attn supported kernel sizes
- [Quantization] Support Quark W8A8 INT8 MoE inference
- [Bugfix] Disable TMA on Blackwell GPUs to fix Triton autotuner OOM in fla/solve_trilfix: disable TMA on Blackwell (sm_12x) to prevent Triton autotuner OO…
- Docs
- Python not yet supported