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 supported49 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [Frontend] Condition /v1/translations on the requested target language
- [Perf][Attention] Reuse KV loads across DiffKV prefill query positions
- [MM] Fix compiled ViT attention output layouts
- [Bugfix][Model] MiMo-V2: skip fused fp8 qkv_proj tensors for layers the model does not have
- [Bugfix][Offload] UVA offload: allocate exact-size pinned host memory instead of Tensor.pin_memory()
- [Frontend] Stream /v1/translations for the encoder-decoder direct path
- [Frontend] Resolve target language to decoder token ids for /v1/translations
- [CI] Split (B200) LM Eval Humming Activation FP8/INT8 into per-model jobs
- [Model] Support Kimi K3 NVFP4 FlashInfer MegaMoE
- [AuxOutput] Only require Model Runner V2 on GPU platform
- Docs
- Python not yet supported