[ROCm][CI/Build] Update ROCm dockerfiles (#30991)

Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>

docker/Dockerfile.rocm

@@ -130,6 +130,7 @@ RUN --mount=type=bind,from=export_vllm,src=/,target=/install \
     && uv pip install --system *.whl
 
 ARG COMMON_WORKDIR
+ARG BASE_IMAGE
 
 # Copy over the benchmark scripts as well
 COPY --from=export_vllm /benchmarks ${COMMON_WORKDIR}/vllm/benchmarks
@@ -144,4 +145,9 @@ ENV SAFETENSORS_FAST_GPU=1
 # Performance environment variable.
 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
+
 CMD ["/bin/bash"]

docker/Dockerfile.rocm_base

-ARG BASE_IMAGE=rocm/dev-ubuntu-22.04:7.1-complete
-ARG TRITON_BRANCH="57c693b6"
+ARG BASE_IMAGE=rocm/dev-ubuntu-22.04:7.0-complete
+ARG TRITON_BRANCH="a272dfa8"
 ARG TRITON_REPO="https://github.com/ROCm/triton.git"
-ARG PYTORCH_BRANCH="1c57644d"
-ARG PYTORCH_VISION_BRANCH="v0.23.0"
+ARG PYTORCH_BRANCH="89075173"
 ARG PYTORCH_REPO="https://github.com/ROCm/pytorch.git"
+ARG PYTORCH_VISION_BRANCH="v0.24.1"
 ARG PYTORCH_VISION_REPO="https://github.com/pytorch/vision.git"
 ARG PYTORCH_AUDIO_BRANCH="v2.9.0"
 ARG PYTORCH_AUDIO_REPO="https://github.com/pytorch/audio.git"
 ARG FA_BRANCH="0e60e394"
 ARG FA_REPO="https://github.com/Dao-AILab/flash-attention.git"
-ARG AITER_BRANCH="59bd8ff2"
+ARG AITER_BRANCH="6af8b687"
 ARG AITER_REPO="https://github.com/ROCm/aiter.git"
 
 FROM ${BASE_IMAGE} AS base