Revert "Update AMD Dockerfile: ROCm 7.2, latest aiter, remove multi-GPU deps"

This reverts commit bdc4523.

Author: Mark Saroufim

docker/amd-docker.Dockerfile

@@ -1,6 +1,8 @@
 FROM ghcr.io/actions/actions-runner:latest
 
 ENV CXX=clang++
+ENV UCX_CXX=g++
+ENV UCX_CC=gcc
 
 RUN sudo apt-get update -y \
     && sudo apt-get install -y software-properties-common \
@@ -33,20 +35,18 @@ RUN sudo groupadd -g 109 render
 RUN sudo apt update -y \
     && sudo apt install -y "linux-headers-$(uname -r)" "linux-modules-extra-$(uname -r)" \
     && sudo usermod -a -G render,video runner \
-    && wget https://repo.radeon.com/amdgpu-install/7.2/ubuntu/jammy/amdgpu-install_7.2.70200-1_all.deb \
-    && sudo apt install -y ./amdgpu-install_7.2.70200-1_all.deb \
+    && wget https://repo.radeon.com/amdgpu-install/6.3.1/ubuntu/jammy/amdgpu-install_6.3.60301-1_all.deb \
+    && sudo apt install -y ./amdgpu-install_6.3.60301-1_all.deb \
     && sudo apt update -y \
     && sudo apt install -y rocm
 
-ENV ROCM_PATH=/opt/rocm
-
 RUN sudo pip install --upgrade pip
 
-RUN sudo pip install --no-cache-dir torch --index-url https://download.pytorch.org/whl/nightly/rocm7.2
+RUN sudo pip install --no-cache-dir torch==2.10.0.dev20250916+rocm6.3 pytorch-triton-rocm --index-url https://download.pytorch.org/whl/nightly/rocm6.3
 
 RUN git clone --recursive https://github.com/ROCm/aiter.git \
     && cd aiter \
-    && git checkout f3be04a12a0cfd6b5e2c7a94edc774f1bc24460d \
+    && git checkout 1d88633958236e942cba3c283864282f7af3ebc5 \
     && sudo pip install -r requirements.txt \
     && sudo python3 setup.py develop
 
@@ -62,4 +62,60 @@ RUN sudo pip install \
 
 RUN sudo pip install git+https://github.com/ROCm/iris.git
 
-ENV LD_LIBRARY_PATH="/opt/rocm/lib"
+RUN sudo apt-get update -y \
+    && sudo apt-get install -y --no-install-recommends \
+    autoconf \
+    automake \
+    libtool \
+    pkg-config \
+    build-essential \
+    gfortran \
+    flex \
+    bison \
+    libomp-dev \
+    libhwloc-dev \
+    libnuma-dev \
+    && sudo rm -rf /var/lib/apt/lists/*
+
+ENV UCX_INSTALL_DIR=/opt/ucx
+ENV OMPI_INSTALL_DIR=/opt/openmpi
+ENV ROCSHMEM_INSTALL_DIR=/opt/rocshmem
+ENV ROCM_PATH=/opt/rocm
+
+RUN cd /tmp \
+    && git clone https://github.com/openucx/ucx.git -b v1.17.x \
+    && cd ucx \
+    && ./autogen.sh \
+    && CC=gcc CXX=g++ ./configure --prefix=${UCX_INSTALL_DIR} --with-rocm=${ROCM_PATH} --enable-mt --disable-optimizations \
+    && make -j$(nproc) \
+    && sudo make install \
+    && cd / \
+    && sudo rm -rf /tmp/ucx
+
+RUN cd /tmp \
+    && git clone --recursive https://github.com/open-mpi/ompi.git -b v5.0.x \
+    && cd ompi \
+    && ./autogen.pl \
+    && ./configure --prefix=${OMPI_INSTALL_DIR} --with-rocm=${ROCM_PATH} --with-ucx=${UCX_INSTALL_DIR} \
+    && make -j$(nproc) \
+    && sudo make install \
+    && cd / \
+    && sudo rm -rf /tmp/ompi
+
+ENV PATH="${OMPI_INSTALL_DIR}/bin:${PATH}"
+ENV LD_LIBRARY_PATH="${OMPI_INSTALL_DIR}/lib:${UCX_INSTALL_DIR}/lib:/opt/rocm/lib"
+
+
+RUN cd /tmp \
+    && git clone https://github.com/ROCm/rocSHMEM.git \
+    && cd rocSHMEM \
+    && mkdir build \
+    && cd build \
+    && MPI_ROOT=${OMPI_INSTALL_DIR} UCX_ROOT=${UCX_INSTALL_DIR} CMAKE_PREFIX_PATH="${ROCM_PATH}:$CMAKE_PREFIX_PATH" \
+       sudo ../scripts/build_configs/ipc_single -DCMAKE_INSTALL_PREFIX=/opt/rocshmem \
+    && cd / \
+    && sudo rm -rf /tmp/rocSHMEM
+
+
+ENV ROCSHMEM_INSTALL_DIR=${ROCSHMEM_INSTALL_DIR}
+ENV LD_LIBRARY_PATH="${ROCSHMEM_INSTALL_DIR}/lib:${LD_LIBRARY_PATH}"