server: preserve RAM prompt cache across slot reuse - #2

server: preserve RAM prompt cache across slot reuse#2

novkien merged 9 commits into

masternovkien/llama.cpp-fork:masterfrom

design/issue-1-kv-cache-retentionnovkien/llama.cpp-fork:design/issue-1-kv-cache-retentionCopy head branch name to clipboard