#!/usr/bin/env bash
# Serve the Qwen3.8-27B HauhauCS Aggressive IQ4_XS on Dankserver (RTX 3090).
#
# Runs a patched llama-server (HauhauCS FastMTP build, commit 4df29be +
# HauhauCS-FastMTP-llama.cpp.patch) with the FastMTP draft sidecar and the
# ngram-mod fallback. There is no pipeline split: the whole model lives on
# the 3090.
#
# The FastMTP draft sidecar requires the patched executable. Loading the
# draft with the stock binary fails with "expected 5120, 248320, got 5120,
# 32768" (see the HauhauCS repo README).
#
# 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) -------------------
: "${MODEL_DIR:=/home/dank/models/hauhaucs-qwen38}"
: "${MODEL_FILE:=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf}"
: "${DRAFT_FILE:=Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-FastMTP-32K.gguf}"
: "${LLAMA_BIN:=/home/dank/llama.cpp-fastmtp/build/bin/llama-server}"
: "${ALIAS:=frank-default-large}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${CTX_SIZE:=131072}"
: "${PARALLEL:=1}"
: "${SPEC_DEFAULT:=1}"
: "${MTP:=1}"
: "${SPEC_DRAFT_N_MAX:=2}"
: "${SPEC_DRAFT_NGL:=all}"
: "${SPEC_DRAFT_P_MIN:=0}"
: "${SPEC_NGRAM_MOD_N_MIN:=48}"
: "${SPEC_NGRAM_MOD_N_MAX:=64}"
: "${SPEC_NGRAM_MOD_N_MATCH:=24}"
: "${CACHE_TYPE_K:=q8_0}"
: "${CACHE_TYPE_V:=f16}"
: "${BATCH_SIZE:=2048}"
: "${UBATCH_SIZE:=1024}"
: "${TEMPERATURE:=1.0}"
: "${TOP_K:=20}"
: "${TOP_P:=0.95}"
: "${MIN_P:=0.0}"
: "${THREADS:=8}"
: "${THREADS_HTTP:=1}"
: "${VERBOSITY:=4}"

MODEL="$MODEL_DIR/$MODEL_FILE"
DRAFT="$MODEL_DIR/$DRAFT_FILE"

if [[ ! -f "$MODEL" ]]; then
    echo "missing required file: $MODEL" >&2
    exit 1
fi
if [[ ! -f "$DRAFT" ]]; then
    echo "missing draft file: $DRAFT" >&2
    exit 1
fi
if [[ ! -x "$LLAMA_BIN" ]]; then
    echo "missing llama-server binary: $LLAMA_BIN" >&2
    exit 1
fi

# --- speculative decoding: FastMTP (MTP) first, then ngram-mod fallback ----
SPEC_ARGS=()
SPEC_ARGS+=(--spec-type draft-mtp)
SPEC_ARGS+=(--spec-draft-model "$DRAFT")
SPEC_ARGS+=(--spec-draft-n-max "$SPEC_DRAFT_N_MAX")
SPEC_ARGS+=(--spec-draft-ngl "$SPEC_DRAFT_NGL")
SPEC_ARGS+=(--spec-draft-p-min "$SPEC_DRAFT_P_MIN")
if [[ "$SPEC_DEFAULT" == "1" ]]; then
    SPEC_ARGS+=(--spec-default)
    SPEC_ARGS+=(--spec-ngram-mod-n-min "$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")
fi

exec "$LLAMA_BIN" \
    --model "$MODEL" \
    "${SPEC_ARGS[@]}" \
    --gpu-layers all \
    --no-mmap \
    --flash-attn on \
    --ctx-size "$CTX_SIZE" \
    --parallel "$PARALLEL" \
    --cache-type-k "$CACHE_TYPE_K" \
    --cache-type-v "$CACHE_TYPE_V" \
    --batch-size "$BATCH_SIZE" \
    --ubatch-size "$UBATCH_SIZE" \
    --temp "$TEMPERATURE" \
    --top-k "$TOP_K" \
    --top-p "$TOP_P" \
    --min-p "$MIN_P" \
    --threads "$THREADS" \
    --threads-http "$THREADS_HTTP" \
    --jinja \
    --alias "$ALIAS" \
    -lv "$VERBOSITY" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT"