Skip to content

llama/cuda: tiered KV cache (--kv-vram-cells): VRAM head, pinned-host tail in one VMM range - #319

Open
professorpalmer wants to merge 1 commit into
PrismML-Eng:prismfrom
professorpalmer:claude/tiered-kv
Open

llama/cuda: tiered KV cache (--kv-vram-cells): VRAM head, pinned-host tail in one VMM range#319
professorpalmer wants to merge 1 commit into
PrismML-Eng:prismfrom
professorpalmer:claude/tiered-kv

Commits

  1. Commits on Oct 5, 2026