Skip to content

[Python][RunInference] vLLM: prefix-aware batching and capacity-based autoscaling - #40908

Draft
AMOOOMA wants to merge 4 commits into
apache:masterfrom
AMOOOMA:pr-vllm-integration
Draft

[Python][RunInference] vLLM: prefix-aware batching and capacity-based autoscaling#40908
AMOOOMA wants to merge 4 commits into
apache:masterfrom
AMOOOMA:pr-vllm-integration

Commits

  1. Commits on Oct 30, 2026