dankclaw: add MTP=1 toggle - prepend draft-mtp before --spec-default ngram-mod fallback

scripts/frank-default-large.env

@@ -19,8 +19,10 @@ CTX_SIZE=524288
 PARALLEL=2
 # Spec: llama.cpp --spec-default preset = ngram-mod (n_match 24, n_min 48,
 # n_max 64).  No draft model.  Switched from DSpark 2026-08-15 after the
-# DSpark multi-slot ROCm crash.  See [[qwen3.8-spec-matrix]].
+# DSpark multi-slot ROCm crash.  MTP=1 prepends the bundled in-model MTP
+# head (draft-mtp) before the ngram-mod fallback.  See [[qwen3.8-spec-matrix]].
 SPEC_DEFAULT=1
+MTP=1
 SPEC_TYPE=
 DRAFT_FILE=
 SPEC_DRAFT_N_MAX=