serverAppConfigs/.AGENTTRASH/serve-frank-large.sh.llama.cpp

#!/usr/bin/env bash
# Serve kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF as
# frank-large via the kingjones30/ROCmFPX llama.cpp runtime on
# Dankclaw (Strix Halo gfx1151, unified memory).
#
# Runtime: kingjones30/ROCmFPX (fork of charlie12345/ROCmFPX with the
# model card's qwen4exp-on-rocmfpx patch) built at
# /home/dank/GitPackages/kingjones-ROCmFPX/build (HIP, gfx1151,
# ROCm 7.2.4, card recipe). The ROCmFP4 quant types plus the qwen4exp
# architecture must be in one tree; stock llama.cpp cannot load this
# GGUF.
#
# Model: Qwen3.8-Flash-Next base (qwen4exp MoE: 512 experts / 10 used,
# 48 layers = 12 attention + 36 SSM, QSA indexer, hyper-connections, PLE
# at layer 1) quantized Q4_0_ROCMFP4_STRIX, 113.47 GiB single file. The
# 50.66 GiB PLE n-gram table stays OUT of GPU memory and streams via
# mmap from the OS page cache — never add --no-mmap or -ot for it.
#
# Profile: card sampling table (temp 0.7, top_p 0.80, top_k 20, min_p 0.0,
# presence 1.5 — non-thinking instruct) mixed with the validated serving
# profile: ctx 401408 x 2 slots, b 4096 / ub 512, t 16 / tb 16, f16 KV,
# fa on (if the graph build aborts on the QSA F16 mask, see the note in
# the env file: port scripts/patches/qwen4exp-qsa-f32-mask.patch into
# this tree and rebuild), cont-batching, prompt cache + 8 GiB cache-ram
# + idle-slot cache, 16 ctx checkpoints, --fit off (auto-fit segfaults
# on qwen4exp hyper-connection config). Speculative decoding off: the
# Flash-Next MTP heads do not load on this loader; the card ships no
# spec flags.
set -euo pipefail

SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-large.env}"
if [[ -f "$ENV_FILE" ]]; then
    set -a
    # shellcheck disable=SC1090
    source "$ENV_FILE"
    set +a
fi

# --- defaults (used when the env file does not set them) -------------------
: "${LLAMA_BIN:=/home/dank/GitPackages/kingjones-ROCmFPX/build/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX}"
: "${MODEL_FILE:=Qwen3.8-Flash-Next-Q4_0-ROCmFP4-STRIX.gguf}"
: "${MMPROJ_PATH:=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf}"
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
: "${CHAT_TEMPLATE_KWARGS:={}}"
: "${ALIAS:=frank-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${CTX_SIZE:=401408}"
: "${PARALLEL:=2}"
: "${BATCH_SIZE:=4096}"
: "${UBATCH_SIZE:=512}"
: "${NUM_THREADS:=16}"
: "${THREAD_BATCH:=16}"
: "${CACHE_TYPE_K:=f16}"
: "${CACHE_TYPE_V:=f16}"
: "${CTX_CHECKPOINTS:=16}"
: "${CACHE_RAM:=8192}"
: "${SLOT_SAVE_PATH:=$SCRIPT_DIR/slot-state}"
: "${SPLIT_MODE:=none}"
: "${FIT:=off}"
: "${NGL:=999}"
: "${FLASH_ATTN:=on}"
: "${TEMPERATURE:=0.7}"
: "${TOP_K:=20}"
: "${TOP_P:=0.8}"
: "${MIN_P:=0.0}"
: "${PRESENCE_PENALTY:=1.5}"
: "${REASONING:=on}"
: "${REASONING_FORMAT:=deepseek}"
: "${HSA_OVERRIDE_GFX_VERSION:=11.5.1}"
: "${SPEC_TYPE:=none}"
: "${DRAFT_MODEL_DIR:=/home/dank/models/mtp-Qwen3.8-Flash-Next-FAST}"
: "${DRAFT_MODEL_FILE:=Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST.gguf}"
: "${SPEC_DRAFT_N_MAX:=3}"
: "${SPEC_DRAFT_N_MIN:=0}"
: "${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" "$CHAT_TEMPLATE_FILE"; do
    if [[ ! -r "$f" ]]; then
        echo "missing or unreadable required artifact: $f" >&2
        exit 1
    fi
done
if [[ ! -x "$LLAMA_BIN" ]]; then
    echo "missing executable runtime: $LLAMA_BIN" >&2
    exit 1
fi

# --- speculative decoding (MTP draft head) ---------------------------------
# The MTP draft head is a separate GGUF sidecar loaded via --spec-draft-model
# (alias --model-draft).  ngram-only specs do not need a draft file.
# Set SPEC_TYPE=none in the env to disable speculative decoding entirely.
SPEC_ARGS=()
if [[ -n "$SPEC_TYPE" && "$SPEC_TYPE" != "none" ]]; then
    SPEC_ARGS=(
        --spec-type "$SPEC_TYPE"
        --spec-draft-n-max "$SPEC_DRAFT_N_MAX"
        --spec-draft-n-min "$SPEC_DRAFT_N_MIN"
        --spec-draft-p-min "$SPEC_DRAFT_P_MIN"
    )
    if [[ "$SPEC_TYPE" == *draft-mtp* ]]; then
        DRAFT_MODEL="$DRAFT_MODEL_DIR/$DRAFT_MODEL_FILE"
        if [[ ! -r "$DRAFT_MODEL" ]]; then
            echo "missing or unreadable draft model: $DRAFT_MODEL" >&2
            exit 1
        fi
        SPEC_ARGS+=(
            --spec-draft-model "$DRAFT_MODEL"
            --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
    if [[ -n "${SPEC_DRAFT_P_SPLIT:-}" ]]; then
        SPEC_ARGS+=(--spec-draft-p-split "$SPEC_DRAFT_P_SPLIT")
    fi
fi

# The STRIX repo ships no mmproj; this is the agentionai FAST package's
# f16 vision tower for the same base model. Passed only when readable.
MMPROJ_ARGS=()
if [[ -n "${MMPROJ_PATH:-}" && -r "${MMPROJ_PATH:-}" ]]; then
    MMPROJ_ARGS=(--mmproj "$MMPROJ_PATH")
fi

SERVER_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
mkdir -p "$SLOT_SAVE_PATH"
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}"

exec /usr/bin/env \
    ROCM_PATH="$ROCM_PATH" \
    HIP_VISIBLE_DEVICES=0 \
    LD_LIBRARY_PATH="$LIBRARY_PATH" \
    HSA_OVERRIDE_GFX_VERSION="$HSA_OVERRIDE_GFX_VERSION" \
    "$LLAMA_BIN" \
    --model "$MODEL" \
    --alias "$ALIAS" \
    --chat-template-file "$CHAT_TEMPLATE_FILE" \
    --chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT" \
    --jinja \
    --device ROCm0 \
    --gpu-layers "$NGL" \
    --split-mode "$SPLIT_MODE" \
    --parallel "$PARALLEL" \
    --ctx-size "$CTX_SIZE" \
    --batch-size "$BATCH_SIZE" \
    --ubatch-size "$UBATCH_SIZE" \
    --fit "$FIT" \
    --flash-attn "$FLASH_ATTN" \
    --cache-type-k "$CACHE_TYPE_K" \
    --cache-type-v "$CACHE_TYPE_V" \
    --threads "$NUM_THREADS" \
    --threads-batch "$THREAD_BATCH" \
    --ctx-checkpoints "$CTX_CHECKPOINTS" \
    --cache-ram "$CACHE_RAM" \
    --slot-save-path "$SLOT_SAVE_PATH" \
    --cache-prompt \
    --cache-idle-slots \
    --metrics \
    --temp "$TEMPERATURE" \
    --top-p "$TOP_P" \
    --top-k "$TOP_K" \
    --min-p "$MIN_P" \
    --presence-penalty "$PRESENCE_PENALTY" \
    --reasoning "$REASONING" \
    --reasoning-format "$REASONING_FORMAT" \
    --reasoning-budget -1 \
    "${MMPROJ_ARGS[@]}" \
    "${SPEC_ARGS[@]}"