[Deps] Retire the CUDA 12 lane (#38404)

Co-authored-by: Mohammad Angkad <mohammad.angkad@radixark.ai>
This commit is contained in:
Mohammad Miadh Angkad
2026-09-10 16:58:09 -07:00
committed by GitHub
co-authored by Mohammad Angkad
parent fae8cd84cb
commit 52c191da52
38 changed files with 170 additions and 737 deletions
+2 -18
View File
@@ -6,7 +6,6 @@ FROM ${BASE_IMAGE}:cuda${CUDA_VERSION}
ARG ARCHITECTURE=x86_64
ARG CUDA_TAG=cu130
ARG CUDA_VERSION=13.0
ARG GDRCOPY_VERSION=2.5.1
ARG NCCL_VERSION=2.30.7
ARG PYTHON_TAG=cp312-cp312
ARG TORCH_VERSION=2.13.0
@@ -49,19 +48,6 @@ RUN set -eux; \
ln -sf "${cuda_stub}" /usr/lib64/libcuda.so; \
ln -sf "${cuda_stub}" "/usr/lib/${ARCHITECTURE}-linux-gnu/libcuda.so"
# DeepEP v2 uses NCCL Gin on CUDA 13. Keep GDRCopy only for the CUDA 12
# legacy NVSHMEM/IBGDA build.
RUN set -eux; \
if [ "${CUDA_TAG}" = cu129 ]; then \
git clone --depth 1 --branch "v${GDRCOPY_VERSION}" \
https://github.com/NVIDIA/gdrcopy.git /opt/gdrcopy; \
make -C /opt/gdrcopy CUDA="${CUDA_HOME}" prefix=/usr/local lib_install; \
printf '%s\n' /usr/local/lib > /etc/ld.so.conf.d/gdrcopy.conf; \
ldconfig; \
test -f /usr/local/include/gdrapi.h; \
ldconfig -p | grep -q libgdrapi; \
fi
RUN --mount=type=cache,id=sgl-deep-ep-pip-${CUDA_TAG}-${PYTHON_TAG}-${ARCHITECTURE},target=/root/.cache/pip \
set -eux; \
"${PYTHON_BIN}" -m pip uninstall -y deep-ep sgl-deep-ep || true; \
@@ -69,10 +55,8 @@ RUN --mount=type=cache,id=sgl-deep-ep-pip-${CUDA_TAG}-${PYTHON_TAG}-${ARCHITECTU
"${PYTHON_BIN}" -m pip install --force-reinstall \
"torch==${TORCH_VERSION}" \
--index-url "https://download.pytorch.org/whl/${CUDA_TAG}"; \
if [ "${CUDA_TAG}" = cu130 ]; then \
"${PYTHON_BIN}" -m pip install --force-reinstall --no-deps \
"nvidia-nccl-cu13==${NCCL_VERSION}"; \
fi; \
"${PYTHON_BIN}" -m pip install --force-reinstall --no-deps \
"nvidia-nccl-cu13==${NCCL_VERSION}"; \
"${PYTHON_BIN}" -m pip install \
"auditwheel>=6.0" \
build \