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 supported51 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- docs: add OrcaRouter deployment framework guide
- [Bugfix][KV offload] Validate computed device pointers before copy
- [Model][Gemma4] Fuse post-attention residual add into pre-FFN RMSNorm
- [Bugfix][Frontend] Recover Kimi K3 tools after omitted think close
- perf: Optimize sliding window cache hit search time complexity to O(N/K) from O(N)
- [Feature]: Cache-aware waiting QoS with optional cooperative prefill preemption
- [Security] Widen int32 pointer arithmetic to int64 in CUDA kernels
- [Bug][ROCm] All-reduce dispatch has an 8–16 MiB "dead zone" on ROCm (CUSTOM's per-world-size table is CUDA-only) that forces PyNCCL/RCCL, which then crashes with `hipErrorLaunchOutOfResources`
- [Bug]: /metrics ignores Prometheus name[] query filters
- [Bug] Hybrid mamba align precopy: illegal memory access on prefix-cache resume with explicit --block-size (state column seeded with wrong block size)
- Docs
- Python not yet supported