Restore historical Q6 large model runtime

This commit is contained in:
Frank committed 2026-08-25 14:23:47 -07:00
1 parent ddfc64013f
commit 6ee195dd8f
3 files changed
+24 -17

No files matched your search

+4 -4
View File
@@ -46,15 +46,15 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
grep -q 'preserve_reasoning":true' "$ENV_FILE"
}
@test "frank-default-large uses Turbo4 only for the V cache" {
@test "frank-default-large uses f16 for both KV cache sides" {
grep -q '^CACHE_TYPE_K=f16$' "$ENV_FILE"
grep -q '^CACHE_TYPE_V=turbo4$' "$ENV_FILE"
grep -q '^CACHE_TYPE_V=f16$' "$ENV_FILE"
grep -qF -- '-ctk "$CACHE_TYPE_K" -ctv "$CACHE_TYPE_V"' "$SERVE_FILE"
}
@test "frank-default-large exposes a swappable ubatch" {
grep -q '^UBATCH_SIZE=512$' "$ENV_FILE"
grep -q ': "${UBATCH_SIZE:=512}"' "$SERVE_FILE"
grep -q '^UBATCH_SIZE=4096$' "$ENV_FILE"
grep -q ': "${UBATCH_SIZE:=4096}"' "$SERVE_FILE"
grep -q -- '-ub "$UBATCH_SIZE"' "$SERVE_FILE"
}