serverAppConfigs/scripts/serve-frank-large.sh

#!/usr/bin/env bash
# Serve jcbtc/Qwen3.8-27B-CIRU-ActiveFPX-PromptForge (v3) as
# frank-default-large via the CIRU ROCmFPX llama.cpp runtime 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 (runtime/qwen38-v3-output-k8-runtime.patch, commit af0eac6 on
# Dankclaw) against the private TheRock ROCm 7.15 SDK (kept in the retired
# ling3-ciru venv). The model is the v3 GGUF with the full-W8 PromptForge
# companion views (FFN/GDN .pfs), the Output-K8 draft proxy, and the BF16
# vision projector. Native depth-4 MTP speculative decoding.
#
# 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. An older system ROCm must not precede them.
#
# Tunables come from frank-default-large.env in this directory unless
# FRANK_LARGE_ENV_FILE overrides that path.
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

# --- 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/CIRU-Qwen3.8-27B-ActiveFPX-v3}"
: "${MODEL_FILE:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-v3-Q8-FFNEQ-LateQ6.gguf}"
: "${FFN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-FFN.pfs}"
: "${GDN_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-GDN.pfs}"
: "${OUTPUT_K8_PFS:=Qwen3.8-27B-CIRU-ActiveFPX-PromptForge-Output-K8.pfs}"
: "${MMPROJ_FILE:=Qwen3.8-27B-mmproj-BF16.mmproj}"
: "${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:=524288}"
: "${PARALLEL:=2}"
: "${BATCH_SIZE:=4096}"
: "${UBATCH_SIZE:=4096}"
: "${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}"
: "${SPEC_DRAFT_P_SPLIT:=0.10}"
: "${TEMPERATURE:=0.7}"
: "${TOP_P:=0.95}"
: "${REASONING:=on}"
: "${REASONING_FORMAT:=deepseek}"
: "${VERBOSITY:=4}"

MODEL="$MODEL_DIR/$MODEL_FILE"
export PROMPTFORGE_SIDECAR="$MODEL_DIR/$FFN_PFS"
export PROMPTFORGE_GDN_SIDECAR="$MODEL_DIR/$GDN_PFS"
# v3 qualified runtime: Output-K8 draft proxy + small-row W8 prompt route.
export PROMPTFORGE_MODE="m2048_fused_tail1476"
export GGML_CUDA_GRAPH_OPT=0
export PROMPTFORGE_ENABLE_SMALLM_W8=1
export PROMPTFORGE_MTP_OUTPUT_K8=1
export PROMPTFORGE_MTP_OUTPUT_K8_VALIDATE=0
export PROMPTFORGE_MTP_OUTPUT_K8_PROXY="$MODEL_DIR/$OUTPUT_K8_PFS"
# The qualified v3 profile disables the CPU argmax draft fast path; the
# Output-K8 proxy + backend sampling replace it. Also drop any IU4/ngram
# companions from the non-IU4 development lane.
unset LLAMA_MTP_CPU_ARGMAX_FASTPATH LLAMA_MTP_BACKEND_GREEDY || true
unset PROMPTFORGE_IU4_SIDECAR PROMPTFORGE_GDN_IU4_SIDECAR || true
unset PROMPTFORGE_ENABLE_NGRAM_MOD PROMPTFORGE_ENABLE_NGRAM_M65_IU4 || true

for f in "$MODEL" "$PROMPTFORGE_SIDECAR" "$PROMPTFORGE_GDN_SIDECAR" "$PROMPTFORGE_MTP_OUTPUT_K8_PROXY" "$MODEL_DIR/$MMPROJ_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

# 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}"

exec "$LLAMA_BIN" \
    --model "$MODEL" \
    --mmproj "$MODEL_DIR/$MMPROJ_FILE" \
    --alias "$ALIAS" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT" \
    -dev ROCm0 \
    -ngl 999 \
    -c "$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 "$CACHE_RAM" \
    --cache-prompt \
    --metrics \
    --no-mmap \
    --spec-type draft-mtp \
    --spec-draft-device ROCm0 \
    --spec-draft-ngl 999 \
    --spec-draft-type-k f16 \
    --spec-draft-type-v f16 \
    --spec-draft-n-max "$SPEC_DRAFT_N_MAX" \
    --spec-draft-n-min "$SPEC_DRAFT_N_MIN" \
    --spec-draft-p-min "$SPEC_DRAFT_P_MIN" \
    --spec-draft-p-split "$SPEC_DRAFT_P_SPLIT" \
    --spec-draft-backend-sampling \
    --temp "$TEMPERATURE" \
    --top-p "$TOP_P" \
    --reasoning "$REASONING" \
    --reasoning-format "$REASONING_FORMAT" \
    --reasoning-budget -1 \
    -lv "$VERBOSITY"