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 supported14 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] Auto-configure TRITON_PTXAS_PATH for new GPU architectures
- Bugfix: zero-initialized metrics for failed/aborted/skipped requests throwing off histograms
- [Bugfix][Quant] fix online fp8 quantization oom
- [Bug]: Use vllm to obtain Qwen3VL last token hidden status
- [ROCm][perf] Shuffle KV cache to use paged_attention_common
- [MoE] Add FusedMoE configs for RTX PRO 6000 Blackwell Max-Q
- fix: Add infinite loop detection for multimodal models (e.g., PaddleOCR-VL)
- [Bugfix] Fix JSONDecodeError when multiple tool_calls in single message
- [Kernel] adding native nccl4py support
- [BugFix] Fix minimax_m2 tool call parser for stream_interval > 1
- Docs
- Python not yet supported