Use conservative four-token MTP drafts

This commit is contained in:
Frank committed 2026-08-25 04:20:15 -07:00
1 parent 3cf6353050
commit f86ed70c71
3 files changed
+7 -8

No files matched your search

+1 -1
View File
@@ -33,7 +33,7 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
grep -qF -- '--spec-draft-n-max "$MTP_N_MAX"' "$SERVE_FILE"
grep -qF -- '--spec-draft-p-min "$MTP_P_MIN"' "$SERVE_FILE"
# qualified profile tunables are exposed in the env
grep -q '^MTP_N_MAX=16$' "$ENV_FILE"
grep -q '^MTP_N_MAX=4$' "$ENV_FILE"
grep -q '^MTP_P_MIN=0.60$' "$ENV_FILE"
grep -q '^SPEC_MTP_STRICT_QWEN=on$' "$ENV_FILE"
grep -q '^MTP_BACKEND_SAMPLING=on$' "$ENV_FILE"