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 supported62 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Bugfix] DeepSeek-V4.1 parser: tolerate drifted DSML tool-call openers
- [Bug][ROCm][MoRIIO] On MI300X (SR-IOV VF), READ mode over XGMI crashes the decode with a GPU memory access fault on its first request
- [Bug]: PIECEWISE CUDA graphs give wrong outputs when vllm::moe_forward is in splitting_ops (fresh output tensor, stale replay address)
- [Bug]: Anthropic Messages silently drops unsupported system content blocks
- [Perf][Attention] FlashInfer prefill for DiffKV attention on SM12x
- [Bugfix][Core] Warn when align mode discards --mamba-block-size
- [CI] Shard PyTorch Fullgraph automatically
- [Bug]: [ROCm] requirements/rocm.txt hard-requires mooncake-transfer-engine-rocm, which has no Python 3.14 wheel
- [Bug]: Qwen Tool Calling errors - 3 parser issues
- [Bugfix][KV Connector] Preserve all KV-cache views in Mooncake Store
- Docs
- Python not yet supported