diff --git a/scripts/serve-frank-large.sh b/scripts/serve-frank-large.sh index 594772f..9625b3d 100755 --- a/scripts/serve-frank-large.sh +++ b/scripts/serve-frank-large.sh @@ -53,6 +53,12 @@ fi : "${NGL:=999}" : "${CPU_MOE:=on}" : "${FLASH_ATTN:=on}" +: "${TEMPERATURE:=0.0}" +: "${REASONING:=on}" +: "${REASONING_FORMAT:=deepseek}" +: "${REASONING_BUDGET:=-1}" +: "${CACHE_RAM:=8192}" +: "${SLOT_SAVE_PATH:=$SCRIPT_DIR/slot-state}" # Hard guard: on this host CUDA pinned host memory strands the co-tenants # (measured 2026-09-15: a default-policy start tried to page-lock 108.12 GiB, # evicted every co-tenant into swap and starved sshd into unreachability