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 supported43 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Feature] NVFP4 dispatch for fused RoPE quantization
- feat: model-agnostic reasoning content detection to prevent per-model parser proliferation
- [Bug]: AMD MI350X/MI355X Kimi K2.5 MXFP4 decode ITL regression v0.18 → v0.19+ (distinct from #43153)
- [KV Offloading] Add metric label and tiering plumbing support
- [Structured Output] Add optional persistent disk cache for compiled xgrammar grammars
- Add tuned fused_moe config for Qwen3-Coder-Next-FP8 on NVIDIA GB10
- [Bugfix] Reject float16 in Marlin MXFP8 kernel selection
- [bugfix][models] Correct torch.compile backend selection for DiffusionGemma
- [Bugfix] Honor override_generation_config for special tokens
- [Bug]: Repeated `start_profile`/`stop_profile` in the same process produces no trace files
- Docs
- Python not yet supported