Enable building MoRI with AMD AINIC stack (#38371)

Signed-off-by: Theresa Shan <thshan@smci355-ccs-aus-n08-21.prov.aus.ccs.cpe.ice.amd.com>
Signed-off-by: Theresa Shan <theresa.shan@amd.com>
Co-authored-by: Theresa Shan <thshan@smci355-ccs-aus-n08-21.prov.aus.ccs.cpe.ice.amd.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>

docker/Dockerfile.rocm

@@ -2,6 +2,11 @@
 ARG REMOTE_VLLM="0"
 ARG COMMON_WORKDIR=/app
 ARG BASE_IMAGE=rocm/vllm-dev:base
+# AMD NIC backend
+ARG NIC_BACKEND=none
+# AMD AINIC apt repo settings
+ARG AINIC_VERSION=1.117.5
+ARG UBUNTU_CODENAME=jammy
 
 # Sccache configuration (only used in release pipeline)
 ARG USE_SCCACHE
@@ -216,6 +221,47 @@ RUN git clone ${DEEPEP_REPO} \
  && git checkout ${DEEPEP_BRANCH} \
  && python3 setup.py --variant rocm --nic ${DEEPEP_NIC} bdist_wheel --dist-dir=/app/deep_install
 
+# MoRI runtime dependencies live in Dockerfile.rocm so NIC backend changes do
+# not force users to rebuild the long-lived Dockerfile.rocm_base image.
+FROM base AS mori_base
+ARG NIC_BACKEND
+ARG AINIC_VERSION
+ARG UBUNTU_CODENAME
+RUN /bin/bash -lc 'set -euo pipefail; \
+ echo "[MORI] Install MoRI proxy deps"; \
+ pip install --quiet --ignore-installed blinker && \
+ pip install --quiet quart msgpack aiohttp pyzmq; \
+ echo "[MORI] NIC_BACKEND=${NIC_BACKEND}"; \
+  \
+  # NIC backend deps — mori auto-detects NIC at runtime (MORI_DEVICE_NIC env var override).
+  # Only vendor packages are installed here for dlopen (e.g. libionic.so); no compile-time flags needed.
+  case "${NIC_BACKEND}" in \
+    # default: mlx5
+    none) \
+      ;; \
+    # AMD NIC
+    ainic) \
+      apt-get update && apt-get install -y --no-install-recommends ca-certificates curl gnupg apt-transport-https && \
+      rm -rf /var/lib/apt/lists/* && mkdir -p /etc/apt/keyrings; \
+      curl -fsSL https://repo.radeon.com/rocm/rocm.gpg.key | gpg --dearmor > /etc/apt/keyrings/amdainic.gpg; \
+      echo "deb [arch=amd64 signed-by=/etc/apt/keyrings/amdainic.gpg] https://repo.radeon.com/amdainic/pensando/ubuntu/${AINIC_VERSION} ${UBUNTU_CODENAME} main" \
+        > /etc/apt/sources.list.d/amdainic.list; \
+      apt-get update && apt-get install -y --no-install-recommends \
+          libionic-dev \
+          ionic-common \
+      ; \
+      rm -rf /var/lib/apt/lists/*; \
+      ;; \
+    # TODO: Add Broadcom bnxt packages/repos here later.
+    # bnxt) \
+    #   echo "[MORI] Add Broadcom bnxt packages/repos here later."; \
+    #   ;; \
+    *) \
+      echo "ERROR: unknown NIC_BACKEND=${NIC_BACKEND}. Use one of: none, ainic"; \
+      exit 2; \
+      ;; \
+  esac;'
+
 # -----------------------
 # vLLM wheel release build stage (for building distributable wheels)
 # This stage pins dependencies to custom ROCm wheel versions and handles version detection
@@ -294,7 +340,7 @@ COPY --from=build_vllm_wheel_release ${COMMON_WORKDIR}/vllm/vllm/v1 /vllm_v1
 
 # -----------------------
 # Test vLLM image
-FROM base AS test
+FROM mori_base AS test
 
 RUN python3 -m pip install --upgrade pip && rm -rf /var/lib/apt/lists/*
 
@@ -385,7 +431,7 @@ RUN printf '%s\n' \
 
 # -----------------------
 # Final vLLM image
-FROM base AS final
+FROM mori_base AS final
 
 RUN python3 -m pip install --upgrade pip && rm -rf /var/lib/apt/lists/*
 
@@ -422,6 +468,8 @@ RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
 
 ARG COMMON_WORKDIR
 ARG BASE_IMAGE
+ARG NIC_BACKEND
+ARG AINIC_VERSION
 
 # Copy over the benchmark scripts as well
 COPY --from=export_vllm /benchmarks ${COMMON_WORKDIR}/vllm/benchmarks
@@ -439,7 +487,9 @@ ENV HIP_FORCE_DEV_KERNARG=1
 # Workaround for ROCm profiler limits
 RUN echo "ROCTRACER_MAX_EVENTS=10000000" > ${COMMON_WORKDIR}/libkineto.conf
 ENV KINETO_CONFIG="${COMMON_WORKDIR}/libkineto.conf"
-RUN echo "VLLM_BASE_IMAGE=${BASE_IMAGE}" >> ${COMMON_WORKDIR}/versions.txt
+RUN echo "VLLM_BASE_IMAGE=${BASE_IMAGE}" >> ${COMMON_WORKDIR}/versions.txt \
+    && echo "MORI_NIC_BACKEND=${NIC_BACKEND}" >> ${COMMON_WORKDIR}/versions.txt \
+    && echo "AINIC_VERSION=${AINIC_VERSION}" >> ${COMMON_WORKDIR}/versions.txt
 
 CMD ["/bin/bash"]
 

docker/Dockerfile.rocm_base

@@ -11,7 +11,7 @@ ARG FA_BRANCH="0e60e394"
 ARG FA_REPO="https://github.com/Dao-AILab/flash-attention.git"
 ARG AITER_BRANCH="v0.1.10.post3"
 ARG AITER_REPO="https://github.com/ROCm/aiter.git"
-ARG MORI_BRANCH="2d02c6a9"
+ARG MORI_BRANCH="v1.1.0"
 ARG MORI_REPO="https://github.com/ROCm/mori.git"
 
 # Sccache configuration (only used in release pipeline)