From 6a86a9df938686ad4e363b75268b7aa5ac9c215c Mon Sep 17 00:00:00 2001 From: Frank Date: Tue, 11 Aug 2026 01:05:24 -0700 Subject: [PATCH] fix: frank-default-small ctx-size 786432 (3 slots x 262144 each) llama.cpp splits --ctx-size across --parallel slots, so 262144 total gave 87552 per stream. Non-negotiable is 262144 per stream: total pool must be 786432. --- scripts/frank-default-small.env | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/scripts/frank-default-small.env b/scripts/frank-default-small.env index 444aa79..652000f 100644 --- a/scripts/frank-default-small.env +++ b/scripts/frank-default-small.env @@ -4,7 +4,8 @@ MODEL_DIR=/home/dank/models ALIAS=frank-default-small HOST=0.0.0.0 PORT=7770 -CTX_SIZE=262144 +# 3 parallel slots x 262144 ctx each = 786432 total context pool. +CTX_SIZE=786432 PARALLEL=3 SPEC_TYPE=draft-dflash SPEC_N_MAX=7