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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] FlashInfer flashinfer_b12x MoE backend runs W4A16 checkpoints as W4A4
- [Bugfix][Spec Decode] Propagate dictionary hf-overrides to speculative draft models
- [Metrics] Add vllm:kv_load_failed_tokens counter
- [Model] Support ViT full CUDA graph for Qwen3-Omni
- [Model][Hardware][AMD] Fuse MLA Attention + Per-token FP8 Quant
- [RL] Add Connex weight transfer backend
- [Distributed] Allow a plugin to provide the PP GroupCoordinator
- [Core] Let workers report requests whose KV cache was lost
- [Bugfix][Kernel] Use padded intermediate size for non-gated FlashInfer b12x NVFP4 MoE
- [ROCm][Perf][DSv4.1] TP1 MXFP8 GEMM tiles and a pre-quantized wo_b input for DEP8 on MI355X
- Docs
- Python not yet supported