kernel/build.sh

#!/usr/bin/env bash
# Build stable-diffusion.cpp with the sasori TQ{K}P ternary kernel.
#
# The GGUFs in this repo use a CUSTOM ggml quantization type (TQ3P, ggml type id 43) that upstream
# stable-diffusion.cpp does NOT know: an unpatched binary will refuse to load them. These two
# patches add the type end to end (block layout, CPU vec_dot, CUDA dispatch), so this script is
# not optional packaging -- it is how you get a runtime that can read the weights.
#
# Verified 2026-07-29 against sd.cpp master-802-e92e86f / ggml eced84c8 (25 hunks, 0 rejects).
set -euo pipefail
HERE="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
SDCPP_REF="${SDCPP_REF:-master}"          # pin to a tag/sha for a byte-reproducible build
CUDA_ARCH="${CUDA_ARCH:-}"                # e.g. 80 (A100) 86 (3090) 89 (4090) 90 (H100); empty = native
BUILD_CUDA="${BUILD_CUDA:-ON}"

echo "== clone sd.cpp ($SDCPP_REF) =="
[ -d stable-diffusion.cpp ] || git clone --recursive https://github.com/leejet/stable-diffusion.cpp
cd stable-diffusion.cpp
git fetch --all --tags -q
git checkout -q "$SDCPP_REF"
git submodule update --init --recursive -q

echo "== apply the TQ{K}P kernel (into the ggml submodule) =="
cd ggml
# ggml type ids 42..60 must be FREE for the sasori types; if upstream ever claims them the check
# below fails loudly instead of silently producing a binary that misreads every tensor.
grep -q "GGML_TYPE_COUNT   = 42," include/ggml.h || {
  echo "!! this ggml revision does not have COUNT=42: the TQ{K}P type ids would collide."
  echo "!! pin SDCPP_REF to a revision where they are free, or re-port the enum block by hand."
  exit 1; }
for p in cpu cuda; do
  [ "$p" = cuda ] && [ "$BUILD_CUDA" != ON ] && continue
  git apply --check "$HERE/sdcpp-$p.patch" || { echo "!! sdcpp-$p.patch does not apply to $SDCPP_REF"; exit 1; }
  git apply "$HERE/sdcpp-$p.patch"
  echo "   applied sdcpp-$p.patch"
done
cd ..

echo "== build =="
CMAKE_ARGS=(-DCMAKE_BUILD_TYPE=Release -DSD_CUDA="$BUILD_CUDA")
[ -n "$CUDA_ARCH" ] && CMAKE_ARGS+=(-DCMAKE_CUDA_ARCHITECTURES="$CUDA_ARCH")
cmake -B build "${CMAKE_ARGS[@]}"
cmake --build build -j"$(nproc)"

echo
echo "OK -> $(pwd)/build/bin/sd-cli"
echo "Sanity check (the type must be known to the binary):"
echo "  strings build/bin/sd-cli | grep TQ3P"