perf: accelerate INT8 diffusion inference with CUDA fusions (#2235)

docker/Dockerfile.cuda

@@ -1,7 +1,7 @@
 ARG CUDA_VERSION=12.6.3
 ARG UBUNTU_VERSION=24.04
 
-FROM nvidia/cuda:${CUDA_VERSION}-cudnn-devel-ubuntu${UBUNTU_VERSION} AS build
+FROM nvidia/cuda:${CUDA_VERSION}-devel-ubuntu${UBUNTU_VERSION} AS build
 
 # sd-server embeds the web UI at build time, so the build image needs Node/pnpm.
 RUN apt-get update && apt-get install -y --no-install-recommends build-essential git ccache cmake ca-certificates curl gnupg && \
@@ -46,13 +46,14 @@ RUN set -- \
     cmake . -B ./build "$@"
 RUN cmake --build ./build --config Release -j$(nproc)
 
-FROM nvidia/cuda:${CUDA_VERSION}-cudnn-runtime-ubuntu${UBUNTU_VERSION} AS runtime
+FROM nvidia/cuda:${CUDA_VERSION}-runtime-ubuntu${UBUNTU_VERSION} AS runtime
 
 RUN apt-get update && \
     apt-get install --yes --no-install-recommends libgomp1 && \
     apt-get clean
 
 COPY --from=build /sd.cpp/build/bin /sd.cpp/bin
+COPY --from=build /sd.cpp/ggml/src/ggml-cuda/vendors/cutlass/LICENSE.txt /sd.cpp/bin/cutlass.txt
 RUN printf '#!/bin/sh\nexec /sd.cpp/bin/sd-cli "$@"\n' > /sd-cli && \
     printf '#!/bin/sh\nexec /sd.cpp/bin/sd-server "$@"\n' > /sd-server && \
     chmod +x /sd-cli /sd-server