update
This commit is contained in:
@@ -45,22 +45,37 @@ EOT
|
|||||||
ARG NV_PEER_MEM_VERSION="1.2"
|
ARG NV_PEER_MEM_VERSION="1.2"
|
||||||
ENV NV_PEER_MEM_VERSION=${NV_PEER_MEM_VERSION}
|
ENV NV_PEER_MEM_VERSION=${NV_PEER_MEM_VERSION}
|
||||||
ENV NV_PEER_MEM_TAG=${NV_PEER_MEM_VERSION}-0
|
ENV NV_PEER_MEM_TAG=${NV_PEER_MEM_VERSION}-0
|
||||||
RUN <<EOT
|
RUN mkdir -p ${STAGE_DIR} && \
|
||||||
#!/bin/bash
|
git clone https://github.com/Mellanox/nv_peer_memory.git --branch ${NV_PEER_MEM_TAG} ${STAGE_DIR}/nv_peer_memory && \
|
||||||
# install nv_peer_mem
|
cd ${STAGE_DIR}/nv_peer_memory && \
|
||||||
mkdir -p ${STAGE_DIR}
|
./build_module.sh && \
|
||||||
git clone https://github.com/Mellanox/nv_peer_memory.git --branch ${NV_PEER_MEM_TAG} ${STAGE_DIR}/nv_peer_memory
|
cd ${STAGE_DIR} && \
|
||||||
cd ${STAGE_DIR}/nv_peer_memory
|
tar xzf ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_VERSION}.orig.tar.gz && \
|
||||||
./build_module.sh
|
cd ${STAGE_DIR}/nvidia-peer-memory-${NV_PEER_MEM_VERSION} && \
|
||||||
cd ${STAGE_DIR}
|
apt-get update && \
|
||||||
tar xzf ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_VERSION}.orig.tar.gz
|
apt-get --fix-broken install -y && \
|
||||||
cd ${STAGE_DIR}/nvidia-peer-memory-${NV_PEER_MEM_VERSION}
|
apt-get install -y dkms && \
|
||||||
apt-get update
|
dpkg-buildpackage -us -uc && \
|
||||||
apt-get --fix-broken install -y
|
dpkg -i ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_TAG}_all.deb
|
||||||
apt-get install -y dkms
|
|
||||||
dpkg-buildpackage -us -uc
|
# ENV NV_PEER_MEM_VERSION=${NV_PEER_MEM_VERSION}
|
||||||
dpkg -i ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_TAG}_all.deb
|
# ENV NV_PEER_MEM_TAG=${NV_PEER_MEM_VERSION}-0
|
||||||
EOT
|
# RUN <<EOT
|
||||||
|
# #!/bin/bash
|
||||||
|
# # install nv_peer_mem
|
||||||
|
# mkdir -p ${STAGE_DIR}
|
||||||
|
# git clone https://github.com/Mellanox/nv_peer_memory.git --branch ${NV_PEER_MEM_TAG} ${STAGE_DIR}/nv_peer_memory
|
||||||
|
# cd ${STAGE_DIR}/nv_peer_memory
|
||||||
|
# ./build_module.sh
|
||||||
|
# cd ${STAGE_DIR}
|
||||||
|
# tar xzf ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_VERSION}.orig.tar.gz
|
||||||
|
# cd ${STAGE_DIR}/nvidia-peer-memory-${NV_PEER_MEM_VERSION}
|
||||||
|
# apt-get update
|
||||||
|
# apt-get --fix-broken install -y
|
||||||
|
# apt-get install -y dkms
|
||||||
|
# dpkg-buildpackage -us -uc
|
||||||
|
# dpkg -i ${STAGE_DIR}/nvidia-peer-memory_${NV_PEER_MEM_TAG}_all.deb
|
||||||
|
# EOT
|
||||||
|
|
||||||
# base tools
|
# base tools
|
||||||
RUN <<EOT
|
RUN <<EOT
|
||||||
|
|||||||
@@ -27,7 +27,6 @@ services:
|
|||||||
OWNER: "nvidia" # nvcr.io/nvidia/pytorch:24.06-py3
|
OWNER: "nvidia" # nvcr.io/nvidia/pytorch:24.06-py3
|
||||||
LABEL: "pytorch"
|
LABEL: "pytorch"
|
||||||
VERSION: "24.06-py3"
|
VERSION: "24.06-py3"
|
||||||
NV_PEER_MEM_VERSION: "1.2"
|
|
||||||
DS_BUILD_OPS: 1
|
DS_BUILD_OPS: 1
|
||||||
DEEPSPEED_VERSION: "master"
|
DEEPSPEED_VERSION: "master"
|
||||||
DEEPSPEED_INSTALL_FLAGS: "--allow_sudo"
|
DEEPSPEED_INSTALL_FLAGS: "--allow_sudo"
|
||||||
|
|||||||
Reference in New Issue
Block a user