mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-30 06:30:49 -05:00
Adds trace logging in server-context.cpp for slot similarity checking during prompt cache slot selection, including skip reasons and similarity calculation details. Assisted-by: llama.cpp:Qwen3.6-27B
64 KiB
64 KiB