frank-secondary: swap to Gemma4-26B-A4B Q4_K_M, 1x200704, q8_0 KV, MTP via separate assistant file

- MODEL_FILE: Swift-1.5-Qwen3.8-27B RCO-IQ3_XXS -> Gemma4-26B-A4B Q4_K_M
- CTX_SIZE: 229376 (2x114,688) -> 200704 (1x200,704)
- PARALLEL: 2 -> 1
- CACHE_TYPE_K/V: q8_0 (unchanged, FP8 class)
- SPEC_TYPE: draft-mtp (unchanged)
- SPEC_DRAFT_FILE: new — separate MTP assistant file (mtp-gemma-4-26B-A4B-it.gguf)
- serve script: add --spec-draft-model support for separate draft files

scripts/serve-frank-secondary.sh

@@ -67,6 +67,7 @@ fi
 # not carry half a spec pair.
 : "${SPEC_TYPE:=draft-mtp}"
 : "${SPEC_DRAFT_N_MAX:=3}"
+: "${SPEC_DRAFT_FILE:=}"
 : "${NGL:=99}"
 # Vision projector. No colon on purpose: an explicitly empty value means
 # "text-only, on purpose" and must NOT be replaced by the default path.
@@ -89,6 +90,10 @@ fi
 # baseline must not carry half a spec pair.
 if [[ -n "$SPEC_TYPE" && "$SPEC_TYPE" != "none" ]]; then
     EXTRA_ARGS+=(--spec-type "$SPEC_TYPE" --spec-draft-n-max "$SPEC_DRAFT_N_MAX")
+if [[ -n "$SPEC_DRAFT_FILE" ]]; then
+    [[ -e "$SPEC_DRAFT_FILE" ]] || { echo "frank-secondary: missing $SPEC_DRAFT_FILE" >&2; exit 1; }
+    EXTRA_ARGS+=(--spec-draft-model "$SPEC_DRAFT_FILE")
+fi
 fi
 
 # The UVM device node is created lazily by nvidia-modprobe on the first CUDA