frank-default-large: swap to caf-eemin Qwen3.8-27B ROCmI4 embedded-MTP

Replace the retired kingjones ROCmFP4 STRIX MTP payload on Dankclaw with
cafonz/Qwen3.8-27B-ROCmI4-MTP-GGUF (eemin namespace, public), served by the
charlie12345/ROCmFPX llama.cpp build (ROCmI4 W4A4, c49ebdbd) on the Strix Halo
iGPU. Q4_0_ROCMI4 with an embedded NextN/MTP head (no separate draft file);
strict-Qwen MTP n16/p0.60/backend sampling on ROCm0. Binary
/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server; model dir
/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP. Updated serve script + env,
ubatch bench, large-config bats test, docs, AGENTS.md.

scripts/bench-ubatch-rocmi4.sh

@@ -0,0 +1,218 @@
+#!/usr/bin/env bash
+# bench-ubatch-rocmi4.sh — sweep ubatch size at 8k context on the
+# frank-default-large ROCmI4 embedded-MTP stack (dankclaw, gfx1151).
+#
+# Boots one llama-server instance per ubatch on a scratch port with a fixed
+# -b and -c 8192, runs a standardized ~75%-of-ctx prose workload, and reads
+# authoritative prefill/generation tok/s from the server's own print_timing
+# lines. Steps from UBATCH_MIN to UBATCH_MAX inclusive by UBATCH_STEP.
+#
+# Usage:
+#   ./scripts/bench-ubatch-rocmi4.sh
+#   UBATCH_MIN=512 UBATCH_MAX=4096 UBATCH_STEP=512 CTX=8192 RUNS=3 \
+#     ./scripts/bench-ubatch-rocmi4.sh
+#
+# Benchmarking policy: stop the production service first so the GPU is not
+# starved. With STOPSVC=1 the script restarts frank-default-large on exit.
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-default-large.env}"
+if [[ -f "$ENV_FILE" ]]; then
+    set -a
+    # shellcheck disable=SC1090
+    source "$ENV_FILE"
+    set +a
+fi
+
+# --- sweep parameters -------------------------------------------------------
+: "${UBATCH_MIN:=512}"
+: "${UBATCH_MAX:=4096}"
+: "${UBATCH_STEP:=512}"
+: "${CTX:=8192}"                 # 8k contexts
+: "${BENCH_BATCH:=$CTX}"         # fixed batch = ctx, so the full 8k prompt fits
+: "${OUT_TOKENS:=256}"
+: "${RUNS:=3}"                   # decode runs per ubatch
+: "${PORT_BASE:=7894}"           # scratch ports 7894..
+: "${STOPSVC:=0}"                # stop/restart the live unit for a clean GPU
+
+# --- resolved paths (fall back to serve-script defaults) --------------------
+: "${LLAMA_BIN:=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server}"
+: "${MODEL_DIR:=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP}"
+: "${MODEL_FILE:=Qwen3.8-27B-Q4_0_ROCMI4.gguf}"
+: "${MMPROJ_FILE:=mmproj-BF16.gguf}"
+: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
+: "${ALIAS:=frank-default-large}"
+: "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
+: "${GGML_HIP_ENABLE_UNIFIED_MEMORY:=1}"
+: "${MTP_N_MAX:=16}"
+: "${MTP_P_MIN:=0.60}"
+
+MODEL="$MODEL_DIR/$MODEL_FILE"
+MMPROJ="$MODEL_DIR/$MMPROJ_FILE"
+
+for f in "$MODEL" "$CHAT_TEMPLATE_FILE"; do
+    if [[ ! -f "$f" ]]; then
+        echo "missing required file: $f" >&2
+        exit 1
+    fi
+done
+if [[ ! -x "$LLAMA_BIN" ]]; then
+    echo "missing llama-server binary: $LLAMA_BIN" >&2
+    exit 1
+fi
+
+MMPROJ_ARGS=()
+if [[ -f "$MMPROJ" ]]; then
+    MMPROJ_ARGS=(--mmproj "$MMPROJ")
+fi
+
+STopped=0
+cleanup() {
+    if [ "$STopped" = 1 ]; then
+        echo "=== restarting frank-default-large ==="
+        sudo systemctl restart frank-default-large || true
+        STopped=0
+    fi
+}
+trap cleanup EXIT
+
+stop_live_service() {
+    if [ "$STOPSVC" = 1 ]; then
+        echo "=== stopping frank-default-large for a clean GPU ==="
+        sudo systemctl stop frank-default-large || true
+        STopped=1
+    fi
+}
+
+# wait_health <pid> <port> — poll /health until ready or the server dies.
+wait_health() {
+    local pid="$1" port="$2" i ready=0 crashed=0
+    for i in $(seq 1 900); do
+        if ! kill -0 "$pid" 2>/dev/null; then crashed=1; break; fi
+        if curl -sf "http://127.0.0.1:${port}/health" >/dev/null 2>&1; then
+            ready=1; break
+        fi
+        [ $((i % 10)) = 0 ] && echo -n .
+        sleep 2
+    done
+    [ "$crashed" = 1 ] && { echo " BACKEND_CRASHED (before ready)"; return 2; }
+    [ "$ready" = 1 ] || { echo " FAIL (timeout)"; return 1; }
+    echo " [ready]"
+    return 0
+}
+
+# run_one <ubatch> <port> <out_tokens> <runs> — boot one server instance, run
+# the workload, parse print_timing, print a RESULT line.
+run_one() {
+    local ubatch="$1" port="$2" out_tokens="$3" runs="$4"
+    local log="/tmp/ubatch-${ubatch}-p${port}.log"
+    : > "$log"
+
+    echo "=== ubatch=${ubatch} ctx=${CTX} port=${port} runs=${runs} ==="
+    "$LLAMA_BIN" \
+        --model "$MODEL" \
+        "${MMPROJ_ARGS[@]}" \
+        --chat-template-file "$CHAT_TEMPLATE_FILE" \
+        --chat-template-kwargs '{"enable_thinking":true,"preserve_thinking":true}' \
+        --alias bench-ubatch \
+        --host 127.0.0.1 --port "$port" \
+        -dev ROCm0 -ngl 999 -np 1 \
+        -t 16 -tb 32 \
+        -c "$CTX" -b "$BENCH_BATCH" -ub "$ubatch" \
+        -fa on -ctk f16 -ctv f16 -ctxcp 16 \
+        --cache-ram 8192 --cache-prompt --metrics --no-mmap \
+        --spec-type draft-mtp --spec-mtp-strict-qwen \
+        --spec-draft-device ROCm0 --spec-draft-ngl all \
+        --spec-draft-type-k f16 --spec-draft-type-v f16 \
+        --spec-draft-n-max "$MTP_N_MAX" --spec-draft-n-min 0 \
+        --spec-draft-p-min "$MTP_P_MIN" \
+        --spec-draft-backend-sampling \
+        --temp 0.7 --top-p 0.95 \
+        --reasoning on --reasoning-format deepseek --reasoning-budget -1 \
+        -lv 4 >>"$log" 2>&1 &
+    local pid=$!
+    wait_health "$pid" "$port" || { tail -30 "$log"; return 2; }
+
+    # one python pass per run; reuse the same boot across runs
+    local r
+    for r in $(seq 1 "$runs"); do
+        echo "--- run ${r}/${runs} ---"
+        python3 - "$ubatch" "$port" "$out_tokens" "$CTX" "$log" <<'PY'
+import sys, time, json, urllib.request
+ubatch, port, out_tokens, ctx, log = sys.argv[1], sys.argv[2], int(sys.argv[3]), int(sys.argv[4]), sys.argv[5]
+
+# Flowing prose at ~75% of ctx so MTP acceptance is realistic.
+VAR = (
+    "narrative nonfiction blends observation with reflection, ",
+    "and a careful writer lets each clause earn its place ",
+    "in the sentence's rising line, so meaning accumulates slowly. ",
+    "The reader is not hurried; the reader is led. Loose and periodic, ",
+    "the style turns on concrete nouns and verbs that carry weight, ",
+    "and it resists the abstract noun that hides a vague claim. ",
+    "A paragraph is not a list. It is a single turn of thought that ",
+    "opens, develops, and lands. This is the craft of prose. Choose, ",
+    "arrange, and above all omit. Omission is the discipline that ",
+    "keeps the whole clear, and clarity is the courtesy we owe the ",
+    "willing reader."
+)
+n = len(VAR)
+parts = []
+t = 0
+while t * 76 < (ctx * 3) // 4:
+    for k in range(5):
+        parts.append(VAR[(t + k) % n])
+    parts.append(f" This is cued by note {t}. ")
+    t += 1
+prompt = "".join(parts)
+prompt += ("\n\nNow, in a detailed and flowing paragraph, continue this essay about "
+           "the philosophy of language and its influence on modern computation. ")
+
+body = json.dumps({
+    "prompt": prompt, "max_tokens": out_tokens,
+    "temperature": 0.0, "stream": False,
+}).encode()
+req = urllib.request.Request(f"http://127.0.0.1:{port}/v1/completions",
+                             data=body, headers={"Content-Type": "application/json"})
+t0 = time.time()
+with urllib.request.urlopen(req, timeout=7200) as resp:
+    out = json.load(resp)
+dt = time.time() - t0
+pt = out.get("usage", {}).get("prompt_tokens", 0)
+ct = out.get("usage", {}).get("completion_tokens", 0)
+
+lines = open(log, encoding="utf-8", errors="ignore").read().splitlines()
+prefill = [l for l in lines if "prompt eval time" in l]
+evals = [l for l in lines if "eval time" in l and "prompt eval" not in l]
+
+def grab(arr):
+    return arr[-1].strip() if arr else "n/a"
+
+g_tps = ""
+if evals and ct:
+    # eval time line: "eval time = .. ms for N tokens"
+    ev = evals[-1].split("= ")[-1]
+    ms = float(ev.split(" for")[0].strip())
+    g_tps = f"{ct / (ms / 1000):.2f}"
+print(f"== RESULT ubatch={ubatch} run={r} "
+      f"PREFILL={grab(prefill)} GEN_TPS={g_tps} "
+      f"pt={pt} ct={ct} wall={dt:.1f}s")
+PY
+    done
+    kill "$pid" 2>/dev/null || true
+    wait "$pid" 2>/dev/null || true
+}
+
+main() {
+    stop_live_service
+    local idx=0 ubatch port
+    printf "%-10s %-14s %-10s\n" "UBATCH" "PREFILL" "GEN_TPS"
+    for ubatch in $(seq "$UBATCH_MIN" "$UBATCH_STEP" "$UBATCH_MAX"); do
+        port=$((PORT_BASE + idx))
+        run_one "$ubatch" "$port" "$OUT_TOKENS" "$RUNS"
+        idx=$((idx + 1))
+    done
+    echo "=== sweep complete ==="
+}
+
+main "$@"

scripts/frank-default-large.env

@@ -1,75 +1,79 @@
-# Tunables for frank-default-large (CIRU llama.cpp, dankclaw, Strix Halo
-# gfx1151).
+# Tunables for frank-default-large (charlie12345/ROCmFPX, dankclaw, Strix Halo
+# gfx1151, ROCmI4 embedded MTP).
 #
-# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
-# qwen3.8-activefpx-promptforge-v2.3 plus the v3 output-K8 runtime patch
-# serving kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4 (dense, Q6 AGENT
-# GGUF) with the standalone MTP Q4_0 draft head. Alias frank-default-large,
-# port 7770.
+# Runtime: charlie12345/ROCmFPX commit c49ebdbd built with
+# -DGGML_HIP_ROCMI4_W4A4=ON against the system ROCm (/opt/rocm-7.2.4, amdclang
+# 22). Serves caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded
+# MTP, no separate draft head). Alias frank-default-large, port 7770.
 #
-# This model replaced jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge (v3) on
-# 2026-08-24. The new model is a plain ROCmFP4 GGUF (no PromptForge .pfs
-# sidecars, no Output-K8 proxy); the requested file is Q6_.
+# This model replaced kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP on
+# 2026-08-25. The old kingjones ROCmFP4 GGUF + standalone MTP Q4_0 draft are
+# retired on this slot.
 
 # WARNING: do not name any variable TEMP, HOST, or GPU_MAX_HEAP_SIZE. The ROCm
 # HIP runtime reads those bare env vars (see the 2026-08-13 TEMP incident).
 # llama.cpp reads --host/--port/--temp as CLI flags, never as env vars.
 
-# CIRU llama-server binary (ROCmFPX v2.3 + v3 output-K8 patch build, built
-# against the private TheRock ROCm 7.15 SDK kept in the retired ling3-ciru
-# venv). ROCm 7.15 is required for the advertised Strix Halo performance.
-LLAMA_BIN=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server
+# charlie12345/ROCmFPX build with the ROCmI4 W4A4 path.
+LLAMA_BIN=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server
 
-# Model files. Plain dense Qwen3.8-27B ROCmFP4 Q6 AGENT GGUF plus the standalone
-# MTP draft head and the vision projector. Kingjones 2026-08-24.
-MODEL_DIR=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP
-MODEL_FILE=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf
-MTP_DRAFT_FILE=mtp-Qwen3.8-27B-Q4_0.gguf
-MMPROJ_FILE=mmproj-Qwen3.8-27B-Q8_0.gguf
+# Model files: embedded-MTP ROCmI4 GGUF + optional BF16 vision projector.
+MODEL_DIR=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP
+MODEL_FILE=Qwen3.8-27B-Q4_0_ROCMI4.gguf
+MMPROJ_FILE=mmproj-BF16.gguf
+# No separate MTP draft head: the MTP/NextN head is embedded in the main GGUF,
+# so no --model-draft is passed. Kept for scripts that reference the var.
+MTP_DRAFT_FILE=
 
-# Qwen-Sharp chat template (tracked in the repo, staged on the host).
+# Qwen-Sharp chat template (tracked in the repo, staged on the host). The Sharp
+# template drives thinking on by default (medium effort) and produces the
+# peg-native + deepseek chat/reasoning shape the Pi agent expects.
 CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
-# enable_thinking + preserve_thinking on by default in the Sharp template;
-# medium effort default. preserve_thinking keeps <think> blocks in recorded
-# assistant messages (set to false to strip them, true to always keep them).
 CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true}'
 
-# ROCm 7.15 SDK paths (inside the retired ling3-ciru venv).
-ROCM_DEVEL=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel
-ROCM_LIB=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries
-ROCM_CORE=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core
-
+# Alias + network.
 ALIAS=frank-default-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7770
 
-# Serving: 196608 (192K) context, 1 slot. f16 KV, context checkpoints,
-# prompt cache, draft-mtp with standalone Q4_0 head, n_max 4 (the knee for
-# the dense model). Unified memory; rocm-smi reports the 64 GiB budget.
-CTX_SIZE=196608
+# Serving: full 262144 context, 1 slot. f16 KV, context checkpoints, prompt
+# cache, strict-MTP embedded draft on ROCm0. Unified memory; rocm-smi reports
+# the 64 GiB budget. Concurrent requests queue; the server never preempts a
+# running generation.
+CTX_SIZE=262144
 PARALLEL=1
-BATCH_SIZE=8192
-UBATCH_SIZE=8192
+# Batch/ubatch follow the qualified ROCmI4 W4A4 profile (see the bench in
+# scripts/bench-ubatch-rocmi4.sh for the ubatch sweep on 8k contexts).
+BATCH_SIZE=512
+UBATCH_SIZE=256
+NUM_THREADS=16
+THREAD_BATCH=32
 CACHE_TYPE_K=f16
 CACHE_TYPE_V=f16
-CTX_CHECKPOINTS=32
+CTX_CHECKPOINTS=16
 CACHE_RAM=8192
 
-# Dense-model MTP draft (standalone Q4_0 head, n_max 4). No PromptForge .pfs
-# sidecars are loaded; the LLAMA_CPU_ARGMAX fast path stays off.
-SPEC_DRAFT_N_MAX=4
-SPEC_DRAFT_N_MIN=0
-SPEC_DRAFT_P_MIN=0.0
-SPEC_DRAFT_P_SPLIT=0.10
+# Embedded-MTP (qwen35 NextN) qualified profile. The head is in the main GGUF,
+# so the draft runs with all layers on ROCm0 (no --model-draft).
+MTP_N_MAX=16
+MTP_N_MIN=0
+MTP_P_MIN=0.60
+SPEC_MTP_STRICT_QWEN=on
+MTP_BACKEND_SAMPLING=on
+SPEC_DRAFT_NGL=all
 
-# Sampling (kingjones model card / Sharp default).
+# Sampling (Sharp default).
 TEMPERATURE=1.0
 TOP_K=20
 TOP_P=0.95
 
-# Thinking on (Qwen-Sharp template drives thinking on; reasoning format
-# projects the tar into reasoning_content).
+# Thinking on (Sharp template drives it; reasoning format projects the tar into
+# reasoning_content).
 REASONING=on
 REASONING_FORMAT=deepseek
 
+# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
+HSA_OVERRIDE_GFX_VERSION=11.5.1
+GGML_HIP_ENABLE_UNIFIED_MEMORY=1
+
 VERBOSITY=4

scripts/serve-frank-large.sh

@@ -1,22 +1,18 @@
 #!/usr/bin/env bash
-# Serve kingjones777/Qwen3.8-27B-Uncensored-ROCmFP4-STRIX-MTP (dense) as
-# frank-default-large via the CIRU ROCmFPX llama.cpp runtime on Dankclaw
-# (Strix Halo gfx1151).
+# Serve caf-eemin/Qwen3.8-27B-ROCmI4-MTP-GGUF (Q4_0_ROCMI4, embedded MTP) as
+# frank-default-large via the charlie12345/ROCmFPX llama.cpp runtime
+# (ROCmI4 W4A4) on Dankclaw (Strix Halo gfx1151).
 #
-# Runtime: the PromptForge llama-server built from ciru-ai/ROCmFPX tag
-# qwen3.8-activefpx-promptforge-v2.3 (commit 103af8b41) plus the v3 output-K8
-# runtime patch (commit af0eac6), against the private TheRock ROCm 7.15 SDK
-# (kept in the retired ling3-ciru venv). The model is the plain ROCmFP4
-# Q6 AGENT GGUF (no PromptForge .pfs sidecars) with the standalone MTP draft
-# head mtp-Qwen3.8-27B-Q4_0.gguf. The Qwen-Sharp chat template is applied at
-# runtime.
+# Runtime: charlie12345/ROCmFPX pinned at commit
+# c49ebdbd5c9f01ec242369f9e7f7967855f80cba, built with
+# -DGGML_HIP_ROCMI4_W4A4=ON against the system ROCm (/opt/rocm-7.2.4,
+# amdclang 22). The model has an embedded NextN/MTP head in the main GGUF, so
+# a separate draft file is not loaded; the MTP draft runs on ROCm0 with all
+# layers via --spec-draft-ngl all.
 #
-# Spec: dense model -> native MTP draft at n_max 4 (the knee, per the model
-# card). The draft head is a separate Q4_0 GGUF loaded via --model-draft.
-#
-# The model card requires ROCm 7.15 (not the system ROCm 7.2.4) for the
-# advertised Strix Halo performance. LD_LIBRARY_PATH therefore points at the
-# 7.15 SDK libraries first.
+# The qualified MTP profile is strict Qwen MTP (--spec-mtp-strict-qwen) with
+# backend sampling, n_max 16, p_min 0.60 (see the model card and the
+# charlie12345/ROCmFPX ROCMI4 runbook).
 #
 # Tunables come from frank-default-large.env in this directory unless
 # FRANK_LARGE_ENV_FILE overrides that path.
@@ -32,30 +28,32 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
-: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
-: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
-: "${MTP_DRAFT_FILE:=mtp-Qwen3.8-27B-Q4_0.gguf}"
-: "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
+: "${LLAMA_BIN:=/home/dank/rocmi4-qwen38/ROCmFPX/build-rocmi4-w4a4/bin/llama-server}"
+: "${MODEL_DIR:=/home/dank/models/eemin-Qwen3.8-27B-ROCMI4-MTP}"
+: "${MODEL_FILE:=Qwen3.8-27B-Q4_0_ROCMI4.gguf}"
+: "${MMPROJ_FILE:=mmproj-BF16.gguf}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
-: "${ROCM_DEVEL:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_devel}"
-: "${ROCM_LIB:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_libraries}"
-: "${ROCM_CORE:=/home/dank/ling3-ciru/Ling-3.0-Flash-CIRU-int4-Strix-native/.venv/lib/python3.12/site-packages/_rocm_sdk_core}"
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
 : "${CTX_SIZE:=262144}"
 : "${PARALLEL:=1}"
-: "${BATCH_SIZE:=4096}"
-: "${UBATCH_SIZE:=4096}"
+: "${BATCH_SIZE:=512}"
+: "${UBATCH_SIZE:=256}"
+: "${NUM_THREADS:=16}"
+: "${THREAD_BATCH:=32}"
 : "${CACHE_TYPE_K:=f16}"
 : "${CACHE_TYPE_V:=f16}"
 : "${CTX_CHECKPOINTS:=16}"
 : "${CACHE_RAM:=8192}"
-: "${SPEC_DRAFT_N_MAX:=4}"
-: "${SPEC_DRAFT_N_MIN:=0}"
-: "${SPEC_DRAFT_P_MIN:=0.0}"
-: "${SPEC_DRAFT_P_SPLIT:=0.10}"
+# Embedded-MTP (qwen35 NextN) qualified profile. The MTP head lives in the main
+# GGUF, so no standalone draft file is referenced; the draft runs on ROCm0 with all layers.
+: "${MTP_N_MAX:=16}"
+: "${MTP_N_MIN:=0}"
+: "${MTP_P_MIN:=0.60}"
+: "${SPEC_MTP_STRICT_QWEN:=on}"
+: "${MTP_BACKEND_SAMPLING:=on}"
+: "${SPEC_DRAFT_NGL:=all}"
 : "${TEMPERATURE:=1.0}"
 : "${TOP_K:=20}"
 : "${TOP_P:=0.95}"
@@ -63,20 +61,20 @@ fi
 : "${REASONING_FORMAT:=deepseek}"
 : "${CHAT_TEMPLATE_KWARGS:={}}"
 : "${VERBOSITY:=4}"
+# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
+: "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
+: "${GGML_HIP_ENABLE_UNIFIED_MEMORY:=1}"
 
 MODEL="$MODEL_DIR/$MODEL_FILE"
-MTP_DRAFT="$MODEL_DIR/$MTP_DRAFT_FILE"
+MMPROJ="$MODEL_DIR/$MMPROJ_FILE"
 
-# Plain dense model: no PromptForge .pfs sidecars, no Output-K8 proxy, no IU4
-# lane. The v3 MTP is driven by the standalone Q4_0 draft head through the
-# standard draft-mtp path. Unset any leftover PromptForge env lanes.
-unset PROMPTFORGE_SIDECAR PROMPTFORGE_GDN_SIDECAR PROMPTFORGE_MTP_OUTPUT_K8_PROXY || true
-unset PROMPTFORGE_MODE PROMPTFORGE_ENABLE_SMALLM_W8 || true
-unset PROMPTFORGE_MTP_OUTPUT_K8 PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE || true
-unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
-unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true
+# Optional vision projector: load it only if the file exists.
+MMPROJ_ARGS=()
+if [[ -f "$MMPROJ" ]]; then
+    MMPROJ_ARGS=(--mmproj "$MMPROJ")
+fi
 
-for f in "$MODEL" "$MTP_DRAFT" "$MODEL_DIR/$MMPROJ_FILE" "$CHAT_TEMPLATE_FILE"; do
+for f in "$MODEL" "$CHAT_TEMPLATE_FILE"; do
     if [[ ! -f "$f" ]]; then
         echo "missing required file: $f" >&2
         exit 1
@@ -87,13 +85,22 @@ if [[ ! -x "$LLAMA_BIN" ]]; then
     exit 1
 fi
 
-# ROCm 7.15 SDK libraries must precede any system ROCm in LD_LIBRARY_PATH.
-export ROCM_PATH="$ROCM_DEVEL"
-export LD_LIBRARY_PATH="${ROCM_LIB}/lib:${ROCM_CORE}/lib:${ROCM_DEVEL}/lib${LD_LIBRARY_PATH:+:$LD_LIBRARY_PATH}"
+# Any leftover PromptForge env lanes from the previous (kingjones/v3) runtime
+# must stay off; this slot now runs the plain strict-MTP draft-mtp path.
+unset PROMPTFORGE_SIDECAR PROMPTFORGE_GDN_SIDECAR PROMPTFORGE_MTP_OUTPUT_K8_PROXY || true
+unset PROMPTFORGE_MODE PROMPTFORGE_ENABLE_SMALLM_W8 || true
+unset PROMPTFORGE_MTP_OUTPUT_K8 PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE || true
+unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
+unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true
+unset LLAMA_MTP_CPU_ARGMAX_FASTPATH LLAMA_MTP_BACKEND_GREEDY || true
+
+# Strix Halo unified memory + native gfx1151 detection for this ROCmFPX build.
+export HSA_OVERRIDE_GFX_VERSION
+export GGML_HIP_ENABLE_UNIFIED_MEMORY
 
 exec "$LLAMA_BIN" \
     --model "$MODEL" \
-    --mmproj "$MODEL_DIR/$MMPROJ_FILE" \
+    "${MMPROJ_ARGS[@]}" \
     --chat-template-file "$CHAT_TEMPLATE_FILE" \
     --chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
     --alias "$ALIAS" \
@@ -101,32 +108,34 @@ exec "$LLAMA_BIN" \
     --port "$LISTEN_PORT" \
     -dev ROCm0 \
     -ngl 999 \
+    -np "$PARALLEL" \
+    -t "$NUM_THREADS" \
+    -tb "$THREAD_BATCH" \
     -c "$CTX_SIZE" \
     -b "$BATCH_SIZE" \
     -ub "$UBATCH_SIZE" \
     -fa on \
     -ctk "$CACHE_TYPE_K" \
     -ctv "$CACHE_TYPE_V" \
-    -np "$PARALLEL" \
     -ctxcp "$CTX_CHECKPOINTS" \
     --cache-ram "$CACHE_RAM" \
     --cache-prompt \
     --metrics \
     --no-mmap \
     --spec-type draft-mtp \
-    --model-draft "$MTP_DRAFT" \
+    ${SPEC_MTP_STRICT_QWEN:+--spec-mtp-strict-qwen} \
     --spec-draft-device ROCm0 \
-    --spec-draft-ngl 999 \
-    --spec-draft-type-k f16 \
-    --spec-draft-type-v f16 \
-    --spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
-    --spec-draft-n-min "$SPEC_DRAFT_N_MIN" \
-    --spec-draft-p-min "$SPEC_DRAFT_P_MIN" \
-    --spec-draft-p-split "$SPEC_DRAFT_P_SPLIT" \
+    --spec-draft-ngl "$SPEC_DRAFT_NGL" \
+    --spec-draft-type-k "$CACHE_TYPE_K" \
+    --spec-draft-type-v "$CACHE_TYPE_V" \
+    --spec-draft-n-max "$MTP_N_MAX" \
+    --spec-draft-n-min "$MTP_N_MIN" \
+    --spec-draft-p-min "$MTP_P_MIN" \
+    ${MTP_BACKEND_SAMPLING:+--spec-draft-backend-sampling} \
     --temp "$TEMPERATURE" \
     --top-k "$TOP_K" \
     --top-p "$TOP_P" \
     --reasoning "$REASONING" \
     --reasoning-format "$REASONING_FORMAT" \
     --reasoning-budget -1 \
-    -lv "$VERBOSITY"
+    -lv "$VERBOSITY"