DarthAffe/stable-diffusion.cpp
1
0 Fork 0
mirror of https://github.com/leejet/stable-diffusion.cpp.git synced 2026-11-10 19:06:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
leejet authored and GitHub committed 2026-10-28 22:02:46 +08:00
1 parent 8cbe905fdd
commit 77b72a2efe
12 files changed
+113 -128
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docker/Dockerfile.cuda
+3 -2
View File
@@ -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