Merge branch 'release/0.11' into yutji/releasenote-0.11

microsoft · Sep 21, 2024 · a227917 · a227917
2 parents 6ea7a65 + 1d2d054
commit a227917
Show file tree

Hide file tree

Showing 2 changed files with 24 additions and 5 deletions.
diff --git a/dockerfile/cuda11.1.1.dockerfile b/dockerfile/cuda11.1.1.dockerfile
@@ -83,11 +83,13 @@ RUN cd /tmp && \
     rm -rf /tmp/MLNX_OFED_LINUX-${OFED_VERSION}*
 
 # Install HPC-X
+ENV HPCX_VERSION=v2.9.0
 RUN cd /opt && \
-    wget -q https://azhpcstor.blob.core.windows.net/azhpc-images-store/hpcx-v2.8.3-gcc-MLNX_OFED_LINUX-${OFED_VERSION}-ubuntu20.04-x86_64.tbz && \
-    tar xf hpcx-v2.8.3-gcc-MLNX_OFED_LINUX-${OFED_VERSION}-ubuntu20.04-x86_64.tbz && \
-    ln -s hpcx-v2.8.3-gcc-MLNX_OFED_LINUX-${OFED_VERSION}-ubuntu20.04-x86_64 hpcx && \
-    rm hpcx-v2.8.3-gcc-MLNX_OFED_LINUX-${OFED_VERSION}-ubuntu20.04-x86_64.tbz
+    rm -rf hpcx && \
+    wget -q https://content.mellanox.com/hpc/hpc-x/${HPCX_VERSION}/hpcx-${HPCX_VERSION}-gcc-inbox-ubuntu20.04-x86_64.tbz -O hpcx.tbz && \
+    tar xf hpcx.tbz && \
+    mv hpcx-${HPCX_VERSION}-gcc-inbox-ubuntu20.04-x86_64 hpcx && \
+    rm hpcx.tbz
 
 # Install NCCL RDMA SHARP plugins
 RUN cd /tmp && \

diff --git a/dockerfile/cuda12.4.dockerfile b/dockerfile/cuda12.4.dockerfile
@@ -8,7 +8,7 @@ FROM nvcr.io/nvidia/pytorch:24.03-py3
 #   - CUDA: 12.4.0
 #   - cuDNN: 9.0.0.306
 #   - cuBLAS: 12.4.2.65
-#   - NCCL: v2.20
+#   - NCCL: v2.23.4-1
 #   - TransformerEngine 1.4
 # Mellanox:
 #   - OFED: 23.07-0.5.1.2
@@ -115,6 +115,23 @@ RUN cd /tmp && \
     mv amd-blis /opt/AMD && \
     rm -rf aocl-blis-linux-aocc-4.0.tar.gz
 
+# Install NCCL 2.23.4
+RUN cd /tmp && \
+    git clone -b v2.23.4-1 https://github.com/NVIDIA/nccl.git && \
+    cd nccl && \
+    make -j ${NUM_MAKE_JOBS} src.build && \
+    make install && \
+    rm -rf /tmp/nccl
+
+# Install UCX v1.16.0 with multi-threading support
+RUN cd /tmp && \
+    wget https://github.com/openucx/ucx/releases/download/v1.16.0/ucx-1.16.0.tar.gz && \
+    tar xzf ucx-1.16.0.tar.gz && \
+    cd ucx-1.16.0 && \
+    ./contrib/configure-release-mt --prefix=/usr/local && \
+    make -j ${NUM_MAKE_JOBS} && \
+    make install
+
 ENV PATH="${PATH}" \
     LD_LIBRARY_PATH="/usr/local/lib:/usr/local/mpi/lib:${LD_LIBRARY_PATH}" \
     SB_HOME=/opt/superbench \