dankclaw: switch frank-default-large to unsloth Qwen3.8-27B UD-Q8_K_XL

- rebuild llama.cpp stock to b10433 (9b05354ec) for bundled-MTP support
- MODEL_FILE -> Qwen3.8-27B-UD-Q8_K_XL.gguf; DRAFT_FILE empty (MTP bundled)
- SPEC: draft-mtp, n_max=10, p_min off (~30 t/s stable) - matrix winner
- CTX 524288 / parallel 2 = 262144/slot (matches pi contextWindow)
- serve script: bundled-MTP (no --spec-draft-model), optional --spec-draft-p-min

scripts/serve-llama-frank-large.sh

@@ -1,8 +1,7 @@
 #!/usr/bin/env bash
-# Serve HauhauCS Qwen3.6-27B-Uncensored-HauhauCS-Aggressive:Q8_K_P
-# with DFlash draft speculative decoding (draft-dflash) on dankclaw
-# (AMD Strix Halo gfx1151, ROCm backend).
-# Runtime: llama.cpp llama-server.
+# Serve unsloth Qwen3.8-27B UD-Q8_K_XL on dankclaw with bundled-MTP
+# speculative decoding (draft-mtp). ROCm backend.
+# Runtime: llama.cpp llama-server (>= b10411).
 #
 # Tunables come from frank-default-large.env in this directory unless the
 # FRANK_LARGE_ENV_FILE environment variable overrides that path.
@@ -19,15 +18,15 @@ fi
 
 # --- defaults (used when the env file does not set them) -----------------
 : "${MODEL_DIR:=/home/dank/models}"
-: "${MODEL_FILE:=Qwen3.6-27B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf}"
-: "${DRAFT_FILE:=Qwen3.6-27B-DFlash-Q8_0.gguf}"
+: "${MODEL_FILE:=Qwen3.8-27B-UD-Q8_K_XL.gguf}"
+: "${DRAFT_FILE:=}"        # empty: Qwen3.8 bundles its MTP drafter in-model
 : "${ALIAS:=frank-default-large}"
 : "${HOST:=0.0.0.0}"
 : "${PORT:=7770}"
-: "${CTX_SIZE:=602100}"
-: "${PARALLEL:=3}"
-: "${SPEC_TYPE:=draft-dflash}"
-: "${SPEC_DRAFT_N_MAX:=8}"
+: "${CTX_SIZE:=262144}"   # Qwen3.8 native context (env may raise for parallel≥2)
+: "${PARALLEL:=2}"
+: "${SPEC_TYPE:=draft-mtp}"
+: "${SPEC_DRAFT_N_MAX:=10}"
 : "${SPEC_NGRAM_MOD_N_MIN:=48}"
 : "${SPEC_NGRAM_MOD_N_MAX:=64}"
 : "${SPEC_NGRAM_MOD_N_MATCH:=24}"
@@ -53,16 +52,19 @@ if [[ ! -f "$MODEL" ]]; then
     exit 1
 fi
 
-# Draft-model flags apply only to spec types that use a draft file
-# (draft-dflash, draft-mtp, draft-eagle3). ngram-mod is draftless.
+# Draft-model flag applies only when a separate draft file is provided.
+# Qwen3.8 bundles MTP in-model; leave DRAFT_FILE empty to use bundled MTP.
 SPEC_ARGS=()
-if [[ "$SPEC_TYPE" == *draft-* ]]; then
+if [[ -n "$DRAFT_FILE" ]]; then
     if [[ ! -f "$DRAFT" ]]; then
         echo "missing required file: $DRAFT" >&2
         exit 1
     fi
     SPEC_ARGS+=(--spec-draft-model "$DRAFT")
 fi
+if [[ -n "${SPEC_DRAFT_P_MIN:-}" ]]; then
+    SPEC_ARGS+=(--spec-draft-p-min "$SPEC_DRAFT_P_MIN")
+fi
 
 exec "$LLAMA_SERVER" \
     --model "$MODEL" \