frank-default-large: add MTP draft head (EasiiX Q8_0, draft-mtp+ngram-mod)

Add speculative decoding via EasiiX/Qwen3.8-Flash-Next-MTP-Strix-Halo-GGUF
Q8_0 sidecar (4.1 GB, qwen4exp architecture matching the main model).

- serve-frank-large.sh: SPEC_ARGS array, draft model existence check,
  spec defaults (n_max 4, p_min 0.75, ngl 999, ROCm0)
- frank-default-large.env: MTP tunables section, fix 'no MTP' comment
- kingjones-strix-rocmfp4.md: MTP Draft Head section, spec flags in
  serving profile, EasiiX + PR #27739 citations

Set SPEC_TYPE=none in the env to disable speculative decoding.

scripts/frank-default-large.env

@@ -17,7 +17,8 @@
 # (count=4, low_rank=320), PLE (layer 1, ngram_size=3, heads_per_ngram=8).
 # Q4_0_ROCMFP4_STRIX quant (file_type=105), 113.47 GiB, single GGUF file.
 # PLE table: 50.66 GiB Q8_0, streamed from page cache (never in GPU VRAM).
-# Text-only (no mmproj, no MTP draft head).
+# Text-only (no mmproj).  MTP draft head loaded as a separate GGUF sidecar
+# (EasiiX/Qwen3.8-Flash-Next-MTP-Strix-Halo-GGUF, Q8_0, 4.1 GB).
 #
 # Context: 262144 (256k) x 2 slots.  f16 KV cache (~6.4 GiB per slot,
 # ~12.8 GiB total).  --fit off because the auto-fit code segfaults on this
@@ -82,4 +83,20 @@ REASONING_FORMAT=deepseek
 # Strix Halo unified memory + native gfx1151.
 HSA_OVERRIDE_GFX_VERSION=11.5.1
 
-VERBOSITY=4
+VERBOSITY=4
+
+# MTP draft head (speculative decoding).  The MTP head from
+# Qwen/Qwen3.8-Flash-Next, exported as a standalone Q8_0 GGUF sidecar by
+# EasiiX/Qwen3.8-Flash-Next-MTP-Strix-Halo-GGUF.  Architecture qwen4exp,
+# matching the main model.  Measured +50% decode on code at temp 0 on
+# Strix Halo (gfx1151).  Set SPEC_TYPE=none to disable.
+DRAFT_MODEL_DIR=/home/dank/models/mtp-Qwen3.8-Flash-Next
+DRAFT_MODEL_FILE=mtp-Qwen3.8-Flash-Next-Q8_0.gguf
+SPEC_TYPE=draft-mtp,ngram-mod
+SPEC_DRAFT_N_MAX=4
+SPEC_DRAFT_N_MIN=0
+SPEC_DRAFT_P_MIN=0.75
+SPEC_DRAFT_NGL=999
+SPEC_DRAFT_DEVICE=ROCm0
+SPEC_DRAFT_TYPE_K=f16
+SPEC_DRAFT_TYPE_V=f16

scripts/serve-frank-large.sh

@@ -21,6 +21,11 @@
 # hyper-connection/indexer configuration; -ngl 999 places all layers on
 # the GPU (SVM-backed).
 #
+# MTP draft head: EasiiX/Qwen3.8-Flash-Next-MTP-Strix-Halo-GGUF (Q8_0,
+# 4.1 GB).  Architecture qwen4exp, matching the main model.  Speculative
+# decoding via --spec-type draft-mtp,ngram-mod (n_max 4, p_min 0.75).
+# Set SPEC_TYPE=none in the env to disable.
+#
 # The Qwen-Sharp chat template (scripts/chat-template.jinja) is applied at
 # runtime so the model emits reasoning in DeepSeek format; the reasoning
 # trail is preserved across turns via CHAT_TEMPLATE_KWARGS.
@@ -63,6 +68,16 @@ fi
 : "${REASONING:=on}"
 : "${REASONING_FORMAT:=deepseek}"
 : "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
+: "${SPEC_TYPE:=draft-mtp,ngram-mod}"
+: "${DRAFT_MODEL_DIR:=$MODEL_DIR}"
+: "${DRAFT_MODEL_FILE:=mtp-Qwen3.8-Flash-Next-Q8_0.gguf}"
+: "${SPEC_DRAFT_N_MAX:=4}"
+: "${SPEC_DRAFT_N_MIN:=0}"
+: "${SPEC_DRAFT_P_MIN:=0.75}"
+: "${SPEC_DRAFT_NGL:=999}"
+: "${SPEC_DRAFT_DEVICE:=ROCm0}"
+: "${SPEC_DRAFT_TYPE_K:=f16}"
+: "${SPEC_DRAFT_TYPE_V:=f16}"
 
 MODEL="$MODEL_DIR/$MODEL_FILE"
 for f in "$LLAMA_BIN" "$MODEL" "$CHAT_TEMPLATE_FILE"; do
@@ -76,6 +91,29 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
     exit 1
 fi
 
+# --- speculative decoding (MTP draft head) --------------------------------
+# The MTP head is loaded as a separate GGUF sidecar via --model-draft.
+# Set SPEC_TYPE=none in the env to disable speculative decoding entirely.
+SPEC_ARGS=()
+if [[ -n "$SPEC_TYPE" && "$SPEC_TYPE" != "none" ]]; then
+    DRAFT_MODEL="$DRAFT_MODEL_DIR/$DRAFT_MODEL_FILE"
+    if [[ ! -r "$DRAFT_MODEL" ]]; then
+        echo "missing or unreadable draft model: $DRAFT_MODEL" >&2
+        exit 1
+    fi
+    SPEC_ARGS=(
+        --spec-type "$SPEC_TYPE"
+        --model-draft "$DRAFT_MODEL"
+        --spec-draft-n-max "$SPEC_DRAFT_N_MAX"
+        --spec-draft-n-min "$SPEC_DRAFT_N_MIN"
+        --spec-draft-p-min "$SPEC_DRAFT_P_MIN"
+        --spec-draft-ngl "$SPEC_DRAFT_NGL"
+        --spec-draft-device "$SPEC_DRAFT_DEVICE"
+        --spec-draft-type-k "$SPEC_DRAFT_TYPE_K"
+        --spec-draft-type-v "$SPEC_DRAFT_TYPE_V"
+    )
+fi
+
 SERVER_DIR="$(cd -- "$(dirname -- "$LLAMA_BIN")" && pwd)"
 ROCM_PATH="${ROCM_PATH:-/opt/rocm}"
 LIBRARY_PATH="$SERVER_DIR:$ROCM_PATH/lib:$ROCM_PATH/lib/rocm_sysdeps/lib:$ROCM_PATH/lib/llvm/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
@@ -117,4 +155,5 @@ exec /usr/bin/env \
     --presence-penalty "$PRESENCE_PENALTY" \
     --reasoning "$REASONING" \
     --reasoning-format "$REASONING_FORMAT" \
-    --reasoning-budget -1
+    --reasoning-budget -1 \
+    "${SPEC_ARGS[@]}"