#!/usr/bin/env bash
# Serve peculiar-ragdoll/Tiel-Coder-35B-A3B (UD-Q6_K_XL) as
# frank-default-small via stock llama.cpp on Dankserver (RTX 3090).
#
# Runtime: upstream llama.cpp (latest master, CUDA build with
# -DGGML_CUDA_FA_ALL_QUANTS=ON -DCMAKE_CUDA_ARCHITECTURES=86).
# The model is a 35B-total / 8-active MoE hybrid (qwen35moe arch) with
# SSM/Mamba layers (full_attention_interval=4: 10 attention + 30 SSM
# layers out of 40).  256 experts, 8 used per token.
#
# Expert offload: --cpu-moe keeps all 256 expert weights in CPU RAM.
# Non-expert weights (attention, SSM, shared expert, embeddings, output)
# are ~1.6 GB and fit entirely on the 24 GB RTX 3090.
#
# KV cache: Q8_0 for both K and V.  With CTX_SIZE=200700 (66 900 per
# slot × 3 parallel) and 10 attention layers (2 KV heads × 256 dim),
# the KV cache is ~2 GB — the requested 2 GB VRAM buffer.
#
# Model is loaded with mmap (default).  The 30 GB Q6_K_XL file is
# memory-mapped; only accessed pages enter RAM.
#
# Tunables come from frank-default-small.env unless FRANK_SMALL_ENV_FILE
# overrides that path.
set -euo pipefail

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

# --- defaults (used when the env file does not set them) -----------------
: "${MODEL_DIR:=/home/dank/models/tiel-coder-35b}"
: "${MODEL_FILE:=Tiel-Coder-35B-A3B-UD-Q6_K_XL.gguf}"
: "${LLAMA_SERVER:=/home/dank/llama.cpp/build/bin/llama-server}"
: "${ALIAS:=frank-default-small}"
: "${BIND_ADDR:=0.0.0.0}"
: "${LISTEN_PORT:=7770}"
: "${CTX_SIZE:=200700}"
: "${PARALLEL:=3}"
: "${CACHE_TYPE_K:=q8_0}"
: "${CACHE_TYPE_V:=q8_0}"
: "${N_GPU_LAYERS:=999}"
: "${BATCH_SIZE:=4096}"
: "${UBATCH_SIZE:=1024}"
: "${VERBOSITY:=2}"
: "${CPU_MOE:=1}"
: "${TEMPERATURE:=1.0}"
: "${TOP_K:=20}"
: "${TOP_P:=0.95}"
: "${MIN_P:=0.0}"
: "${THREADS:=7}"
: "${THREADS_HTTP:=8}"

MODEL="$MODEL_DIR/$MODEL_FILE"

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

exec "$LLAMA_SERVER" \
    --model "$MODEL" \
    $([ "$CPU_MOE" = "1" ] && printf -- "--cpu-moe") \
    --cache-type-k "$CACHE_TYPE_K" \
    --cache-type-v "$CACHE_TYPE_V" \
    --ctx-size "$CTX_SIZE" \
    --parallel "$PARALLEL" \
    --gpu-layers "$N_GPU_LAYERS" \
    --batch-size "$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" \
    --host "$BIND_ADDR" \
    --port "$LISTEN_PORT"