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
- fix(security): validate allowed_token_ids against model output vocab size
- [Bugfix][Model] Remove redundant all_gather_interleave in ViT split_qkv
- [Core][V1] Enforce max_num_partial_prefills and max_long_partial_prefills in V1 scheduler
- [Doc] Document SimpleCPUOffloadConnector in the KV offloading guide
- [Usability] Engine fails to start when available Mamba cache blocks < max_num_seqs (hybrid models + LoRA) — suggest auto-clamping with a warning
- fix(v1): skip full GC during EngineCore process exit
- [ROCm] Enable AITER by default
- [Bug]: moe_wna16_marlin_gemm applies wrong per-row topk weights (mul_topk_weights=True) at gpt-oss NVFP4 MoE shapes — corrupt output
- Add pushed-based ZMQ metrics logger support
- [Feature] Add mamba ssu kernel autotune at warmup time
- Docs
- Python not yet supported