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
- [Bug]: Incoherent output depending on tensor-parallel-size during inference on Leanstral (Mistral Small 4 family)
- [Bug]: CPU DP affinity regression
- [V1][Spec Decode] Overlap bonus sampling with target verification via maybe_execute_in_parallel
- [ROCm][Perf] Enable fused indexer-Q RoPE+quant kernel for DeepSeek/GLM sparse attention
- Respect explicit VLLM_TARGET_DEVICE=tpu on macOS
- fix(build): respect explicit VLLM_TARGET_DEVICE on macOS
- [multimodal] Refactor IPC calculation out of gpu_worker
- [Bugfix][V1] Surface out-of-range token ids as a clear per-request error
- [Kernel] Optimize CuTeDSL DCP top-k merge
- [Model Runner V2][MTP] Share topk index buffer between draft steps
- Docs
- Python not yet supported