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 supported24 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Disable HMA for eagle/MTP with sliding window models
- [ROCm] Fix AssertionError in ActivationQuantFusionPass when torch.compile is used on ROCm
- [Usage]: RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)`
- [BugFix] Dense + multinode + DP > 1 port conflicts
- [Attention] Validate DIFFKV via backend selection
- [SpecDecode] Reduce TP communication for large-vocab draft models in DFlash/PARD speculative decoding
- fix: skip string delimiters in Gemma4 nested array bracket-depth tracking
- fix: Disable VLLM_ROCM_USE_AITER_FP4BMM by default to prevent crashes on MI300X
- [Core]Fix/handle kernel failures
- [WIP] Enable `torch.cond` for dynamic block-scaled MM kernels
- Docs
- Python not yet supported