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
- [Bug]: Error on sleep mode when upgrade into vllm 0.16.0
- [Bug]: Suffix decoding crashes with assert total_num_scheduled_tokens > 0
- Fix bugs in fp8 fused_moe_lora kernels
- [Bug]: [ROCm] ROCM_ATTN backend shows ~8.5% systematic score deviation on Qwen3-VL-Reranker pooling
- install torchaudio for HPU stack (align with vllm-gaudi Dockerfile.hpu)
- [ROCm][Quantization] Enable moe_wna16 on ROCm via Triton fallback
- [ROCm][Quantization] Enable compressed-tensors WNA16 test on ROCm
- [Bug]: vllm 0.16.0+image encountered CUDA error: CUBLAS_STATUS_INVALID_VALUE when calling `cublasGemmEx
- [Bugfix] Fix RoutedExpertsCapturer for pipeline parallelism (PP > 1)
- [Bug]: AllReduceRMSFusionPass crashes with PP
- Docs
- Python not yet supported