vLLM BlogTools
Inkling 2 Small on vLLM: Day-0 Support

vLLM supports Thinking Machines' Inkling 2 Small from day 0: attention residuals, a new decode kernel for relative-bias attention, all-reduce fused with the ops around it, and DSpark speculative…
Read at vLLM Blog ↗Related

ToolsEncoder Disaggregation in vLLM: Scaling Multimodal Serving with EPD vLLM Blog
ToolsMigrating vLLM to the LibTorch Stable ABI vLLM Blog
ToolsIntroducing Kinference: An Open Source Inference Control Plane for vLLM and Kubernetes vLLM Blog

ToolsvLLM Delivers Day-0 Support for Kimi K3.1 Pro vLLM Blog
ToolsDay 0 support for Mistral Large 4 on vLLM vLLM Blog
