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 supported36 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [RFC][kv_offload]: Tiering Admission Policy Design
- [BugFix] Reserve the bonus query slot in DFlash scheduling budget
- [1/N][KV Cache] Add host-resident KV cache offloading for sparse MLA decode
- [Perf][Reasoning] O(delta) reasoning-end check for engine parsers
- [Model] Add Dots3Note language and multimodal support
- [Bugfix] Import each packed IPC export once on the consumer side
- [Bug][Anthropic] /v1/messages canonicalizes model aliases, causing Claude Code to strip thinking blocks during tool-use loops
- [Bug]: Prefix caching is ineffective on Mamba-2/GDN hybrid (Qwen3_5MoeForConditionalGeneration)
- [Bug]: `MiniMAXGemmaRMSNorm` unconditionally calls FlashInfer CUDA kernels, breaking MiniMax-M3 on every non-CUDA platform
- [Quantization][Autoround][XPU] Support AutoRound MXFP8 MoE models
- Docs
- Python not yet supported