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 supported60 Subscribers
View all SubscribersAdd a CodeTriage badge to vllm
Help out
- Issues
- [ROCm][Perf][Qwen3.8] Keep dense mono K2 on during MTP verify.
- [Feature][Frontend] Accept forwarded multimodal features with reused prompt token ids
- [Perf] Fused SynthID-Text sampling with bucketed tournament layers
- [Tests][MRV2] Test padded tokens get PAD slots
- [Rust Frontend] Let the server run over any `Llm`
- [Bugfix] Support PyTorch bin checkpoints in checkpoint_has_lm_head
- [Perf][Kernel] Faster full-warp MoE top-k selection with redux.sync
- [Refactor] Simplify GLM sparse indexer decode grouping with gather
- [WIP] Rust engine http client backup
- [ROCm][Bugfix] Fix AITER shared-expert fusion routing for gate-less MoE (DeepSeek-V2-Lite)
- Docs
- Python not yet supported