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
- [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
- [Bug]: NixlConnector: KV blocks released on lease expiry while remote READ in flight, decode silently consumes overwritten KV
- [ROCm][Perf] Two-level all-reduce for TP=8 across two XGMI islands (8x MI210)
- [Bugfix] Don't force a second </think> after a natural end in V1 spec decode
- [SketchSSM] Add SketchSSM decode for Mamba-2 with Triton kernels
- [Bugfix][CPU] Reject -1 placeholder drafts in the C++ rejection sampler
- [Bug] GLM hybrid-SSM + MTP: deep-ctx agent session sharply degrades (fabricated tool args, self-amnesia) exactly when a concurrent request arrives — persists after #58454/#58368
- Docs
- Python not yet supported