serverAppConfigs/old/scripts/serve-pp-head.sh

#!/usr/bin/env bash
# Serve the Qwen3.8-27B pipeline-parallel head on Dankclaw.
#
# Runs llama-server (b10433) with --rpc pointing at the worker on
# Dankserver. The model is split pipeline-style across [RPC0, iGPU]:
# layers run in order, hidden states cross the ethernet boundary once per
# token step.
#
# IMPORTANT: no --device flag. The RPC device only joins the model's device
# list through default device selection; an explicit --device silently drops
# it. See the header of frank-default-large.env.
#
# Tunables come from frank-default-large.env in this directory unless the
# FRANK_PP_HEAD_ENV_FILE environment variable overrides that path.
set -euo pipefail

SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
ENV_FILE="${FRANK_PP_HEAD_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) -------------------
: "${MODEL_DIR:=/home/dank/models}"
: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_K.gguf}"
: "${HEAD_BIN:=/home/dank/llama.cpp/build/bin/llama-server}"
: "${ALIAS:=frank-pp-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${RPC_SERVERS:=192.168.0.235:50052}"
: "${TENSOR_SPLIT:=1,1}"
: "${CTX_SIZE:=131072}"
: "${PARALLEL:=1}"
: "${SPEC_NONE:=0}"
: "${SPEC_DEFAULT:=1}"
: "${MTP:=0}"
: "${SPEC_DRAFT_N_MAX:=4}"
: "${SPEC_DRAFT_MODEL:=}"
: "${SPEC_NGRAM_MOD_N_MIN:=48}"
: "${SPEC_NGRAM_MOD_N_MAX:=64}"
: "${SPEC_NGRAM_MOD_N_MATCH:=24}"
: "${CACHE_TYPE_K:=q8_0}"
: "${CACHE_TYPE_V:=f16}"
: "${BATCH_SIZE:=8192}"
: "${UBATCH_SIZE:=256}"
: "${TEMPERATURE:=1.0}"
: "${TOP_K:=20}"
: "${TOP_P:=0.95}"
: "${MIN_P:=0.0}"
: "${THREADS:=12}"
: "${THREADS_HTTP:=1}"
: "${VERBOSITY:=4}"
: "${DIRECT_IO:=1}"

MODEL="$MODEL_DIR/$MODEL_FILE"

if [[ ! -f "$MODEL" ]]; then
    echo "missing required file: $MODEL" >&2
    exit 1
fi
if [[ ! -x "$HEAD_BIN" ]]; then
    echo "missing head binary: $HEAD_BIN" >&2
    exit 1
fi

# --- RPC endpoints -----------------------------------------------------------
RPC_ARGS=()
for s in ${RPC_SERVERS//,/ }; do
    RPC_ARGS+=(--rpc "$s")
done

# --- split fractions ---------------------------------------------------------
SPLIT_ARGS=()
if [[ -n "${TENSOR_SPLIT}" ]]; then
    SPLIT_ARGS+=(--tensor-split "${TENSOR_SPLIT}")
fi

# --- speculative decoding -----------------------------------------------------
SPEC_ARGS=()
if [[ "${SPEC_NONE}" == "1" ]]; then
    SPEC_ARGS+=(--spec-type none)
else
    if [[ "${SPEC_DEFAULT}" == "1" ]]; then
        if [[ "${MTP}" == "1" ]]; then
            # MTP first (bundled in-model head by default, or a standalone
            # draft file when SPEC_DRAFT_MODEL is set), then the ngram-mod
            # fallback. Order matters: --spec-type appends to the impl chain.
            SPEC_ARGS+=(--spec-type draft-mtp)
            SPEC_ARGS+=(--spec-draft-n-max "${SPEC_DRAFT_N_MAX}")
            if [[ -n "${SPEC_DRAFT_MODEL}" ]]; then
                if [[ ! -f "${SPEC_DRAFT_MODEL}" ]]; then
                    echo "SPEC_DRAFT_MODEL file missing: ${SPEC_DRAFT_MODEL}" >&2
                    exit 1
                fi
                SPEC_ARGS+=(--spec-draft-model "${SPEC_DRAFT_MODEL}")
            fi
        fi
        SPEC_ARGS+=(--spec-default)
        SPEC_ARGS+=(--spec-ngram-mod-n-min "${SPEC_NGRAM_MOD_N_MIN}")
        SPEC_ARGS+=(--spec-ngram-mod-n-max "${SPEC_NGRAM_MOD_N_MAX}")
        SPEC_ARGS+=(--spec-ngram-mod-n-match "${SPEC_NGRAM_MOD_N_MATCH}")
    else
        echo "SPEC_NONE=0 requires SPEC_DEFAULT=1" >&2
        exit 1
    fi
fi

# --- load mode ----------------------------------------------------------------
LOAD_ARGS=()
if [[ "${DIRECT_IO}" == "1" ]]; then
    LOAD_ARGS+=(--direct-io)
fi

exec "$HEAD_BIN" \
    --model "$MODEL" \
    "${RPC_ARGS[@]}" \
    "${SPLIT_ARGS[@]}" \
    "${SPEC_ARGS[@]}" \
    "${LOAD_ARGS[@]}" \
    --gpu-layers all \
    --fit off \
    --cache-type-k "$CACHE_TYPE_K" \
    --cache-type-v "$CACHE_TYPE_V" \
    --ctx-size "$CTX_SIZE" \
    --parallel "$PARALLEL" \
    --batch-size "$BATCH_SIZE" \
    --ubatch-size "$UBATCH_SIZE" \
    --temp "$TEMPERATURE" \
    --top-k "$TOP_K" \
    --top-p "$TOP_P" \
    --min-p "$MIN_P" \
    --threads "$THREADS" \
    --threads-http "$THREADS_HTTP" \
    --alias "$ALIAS" \
    -lv "$VERBOSITY" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT"