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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][DSv4.1][Perf] Pass no MoE padding to AITER on the a4w4 path
- [Bugfix][Weight Cache] Restore model state before IPC fallback
- [Bugfix][Mamba] Reject stochastic rounding with Triton speculation
- [Bugfix][Benchmark] Fix sweep --resume with warmup and recorded failures
- [LoRA] Add an API to read and update LoRA slot weights
- [Bugfix][Parser] Preserve quoted Qwen3 tool markup in reasoning
- perf: route GLM-5.2 fused-QKV-A GEMM through dsv3_fused_a_gemm on SM10x
- [Core] Complete snapshot recovery before serving
- [Feature]: Support fused MoE weights with NCCL M2N weight transfer
- [Feature]: Support trainer-side pipeline parallelism with NCCL M2N weight transfer
- Docs
- Python not yet supported