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 supported35 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC]: Layerwise and Sparse KV cache offloading to support longer sequence length
- [Bug]: Analysis for an Automated Request Validation and Normalization Module at the Upstream of vLLM (Hard Interception) to Fundamentally Solve DSML Leakage, Garbled Output, and Empty Responses
- [Feature]: Proposal for an Automated Request Validation and Normalization Module at the Upstream of vLLM (Hard Interception) to Fundamentally Solve DSML Leakage, Garbled Output, and Empty Responses
- [Bugfix] Pin FlashInfer bmm_fp8 to cuBLAS on sm_12x to avoid cuDNN hot-path stalls
- [CPU] Add CPU-tuned autotune configs for Mamba2/SSD Triton kernels
- DSpark speculative decoding incompatible with NIXL P/D disaggregation and Hopper FA3
- [Perf][ROCm] Dual-stream decode with hipgraphs
- [Bug]: KV connector "Throughput (MB/s)" sums overlapping transfer durations; propose reporting avg per-transfer throughput instead
- [Bug]: Gemma4 Unified image requests produce all-NaN logits after BF16-to-FP16 fallback
- SIGSEGV in torch::jit::invokeOperatorFromPython (transpose) with NVFP4 + DFlash + torch.compile on Blackwell SM120
- Docs
- Python not yet supported