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 supported26 Subscribers
Add a CodeTriage badge to vllm
Help out
- Issues
- [Core] Avoid using extra thread in `UniProcExecutor`
- Bugfix: fix RMSNormGated input_guard torch.compile dynamo tracing on CUDA
- [Bugfix] Run FlashInfer autotuning before KV cache allocation
- [Spec Decode] Add Sliding Window Attention support to DFlash drafter
- [Benchmark] Support multi-image requests in multimodal samplers
- [Tool Parser] Redesign Qwen3 XML tool parser as character-level state machine
- [Feature] Add --pre-warm-nccl to reduce first-request TTFT on multi-GPU
- [vLLM IR] Fixes for Triton implementations
- [Core] Added Sleep 3 -- Keep weights on GPU, discard KV cache and everything else
- [KV Transfer] Add MooncakeStoreConnector for KV cache offloading via Mooncake distributed store
- Docs
- Python not yet supported