serverAppConfigs/scripts/serve-frank-large.sh

#!/usr/bin/env bash
# Serve kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX as
# frank-default-large via the charlie12345/ROCmFPX llama.cpp fork with
# PR #27742 (qwen4exp architecture) merged, on Dankclaw (Strix Halo
# gfx1151, unified memory).
#
# Runtime: ROCmFPX llama.cpp built at
# /home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server
# with -DGGML_HIP=ON -DGGML_HIP_ROCMI4_W4A4=ON
# -DCMAKE_HIP_ARCHITECTURES=gfx1151 -DLLAMA_BUILD_WEBUI=OFF.
#
# Model: 177B params (56B MoE + 51.2B PLE n-gram table). 512 experts,
# 10 used, 48 layers (12 attention + 36 SSM/Mamba,
# full_attention_interval=4), 2 KV heads x 256 dim, QSA
# indexer (4 heads, top_k=2048), hyper-connections (count=4, low_rank=320),
# PLE (layer 1).  Q4_0_ROCMFP4_STRIX quant, 113.47 GiB, single file.
# PLE table (50.66 GiB Q8_0) streamed from page cache; never in GPU VRAM.
# GPU resident: ~63-69 GiB. Context: up to 131072.
# Loaded with mmap (default) into the Strix Halo unified memory pool.
# --fit off is set because the auto-fit code segfaults on this model's
# hyper-connection/indexer configuration; -ngl 999 places all layers on
# the GPU (SVM-backed).
#
# MTP draft head: both attempted heads (EasiiX Q8_0 and agentionai
# ROCmFP4-FAST) are INCOMPATIBLE with the STRIX_LEAN model — the
# qwen4exp binary expects blk.0.hc_attn_norm.weight which neither
# draft GGUF carries.  Using ngram-mod only.  Set SPEC_TYPE=none in
# the env to disable spec decoding.
#
# 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.
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) -------------------
: "${LLAMA_BIN:=/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server}"
: "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-Flash-Next-ROCmFP4-STRIX}"
: "${MODEL_FILE:=Qwen3.8-Flash-Next-Q4_0-ROCmFP4-STRIX.gguf}"
: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
: "${CHAT_TEMPLATE_KWARGS:={}}"
: "${ALIAS:=frank-default-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${CTX_SIZE:=524288}"
: "${PARALLEL:=2}"
: "${BATCH_SIZE:=4096}"
: "${UBATCH_SIZE:=4096}"
: "${NUM_THREADS:=16}"
: "${THREAD_BATCH:=16}"
: "${CACHE_TYPE_K:=f16}"
: "${CACHE_TYPE_V:=f16}"
: "${CTX_CHECKPOINTS:=16}"
: "${CACHE_RAM:=8192}"
: "${FIT:=off}"
: "${TEMPERATURE:=0.7}"
: "${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}"
: "${SPEC_TYPE:=ngram-mod}"
: "${DRAFT_MODEL_DIR:=$MODEL_DIR}"
: "${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 loaded as a separate GGUF sidecar via --model-draft.
# ngram-only specs (ngram-mod, etc.) do NOT need a draft model 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: $DRAFT_MODEL" >&2
            exit 1
        fi
        SPEC_ARGS+=(
            --model-draft "$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
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}"

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 999 \
    --parallel "$PARALLEL" \
    --ctx-size "$CTX_SIZE" \
    --batch-size "$BATCH_SIZE" \
    --ubatch-size "$UBATCH_SIZE" \
    --fit "$FIT" \
    --flash-attn on \
    --cache-type-k "$CACHE_TYPE_K" \
    --cache-type-v "$CACHE_TYPE_V" \
    --threads "$NUM_THREADS" \
    --threads-batch "$THREAD_BATCH" \
    --ctx-checkpoints "$CTX_CHECKPOINTS" \
    --cache-ram "$CACHE_RAM" \
    --cache-prompt \
    --cache-idle-slots \
    --metrics \
    --temp "$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 "$MMPROJ_PATH" \
    "${SPEC_ARGS[@]}"