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
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [GDN] Avoid two per-layer copies in the FlashInfer prefill path
- [Bug][ROCm][Attention][KV Connector] DeepSeek-V3.2 / GLM-5.x DSA sparse-MLA decode is garbage under CUDA graphs in PD-disaggregation (remote-prefilled KV)
- docs(security): fix endpoint inventory — dev-only RLHF routes, fault_tolerance, metrics
- Fix duplicated word in Elastic EP warning message
- [RFC]: Scheduler-Aware Multi-Tier KV Caching for vLLM with MORI-UMBP
- Allow selecting uvicorn's HTTP protocol implementation
- [Bugfix][XPU] Keep MoE expert weights offloaded during weight post-processing
- [CI] Split (H100) V1 Attention into Sparse MLA, MLA Backends/Correctness, Dense/SSM, and DCP/ROCm jobs
- [Bug]: Hybrid Mamba2 with prefix caching (`mamba_cache_mode="all", should be deterministic`) returns different in same batch
- [Bugfix] Ensure unique verbose JSON segment IDs
- Docs
- Python not yet supported