Reduce large model context to 64K

2026-08-25 04:13:00 -07:00
parent b0eb571321
commit 3cf6353050
4 changed files with 5 additions and 5 deletions
@@ -40,7 +40,7 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
 }

@test "frank-default-large fits the model and KV cache in unified memory" {
-    grep -q '^CTX_SIZE=131072$' "$ENV_FILE"
+    grep -q '^CTX_SIZE=65536$' "$ENV_FILE"
    grep -q ': "${CTX_SIZE:=262144}"' "$SERVE_FILE"
 }