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
- [Refactor] [3/N] Reorganize kernel abstraction directory
- [Bugfix] Propagate default stop_token_ids to per-request SamplingParams
- [MLA] Add fused Triton concat+quantize kernel for fp8 decode queries
- [Perf] Fused Triton kernels for Qwen3-VL vision encoder preprocessing
- feat(cpu): add CPU support for Mamba ShortConv and fix GEMM dispatch
- [Bugfix] LoRA for fused_qkv_a_proj in MLA (DeepSeek V3.2)
- feat: added num requests and num tokens to profiles
- [Bugfix] Fix sleep mode wake_up memory leaks
- [Bug]: RuntimeError: CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasGemmEx
- [Bug]: MTP Speculative Decoding with NVFP4: Weight Shape Mismatch
- Docs
- Python not yet supported