A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[ROCm] Update AITER branch for ROCm base docker (#27586)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Micah Williamson committed
Oct 27, 2025 at 12:22 UTC
921e78f4bbe56d6c9a0e9e609b9b3cfe97a4a51b
1 file changed
+1
-1
docker/Dockerfile.rocm_base
+1
-1
@@ -7,7 +7,7 @@ ARG PYTORCH_REPO="https://github.com/ROCm/pytorch.git"
7
ARG PYTORCH_VISION_REPO="https://github.com/pytorch/vision.git"
8
ARG FA_BRANCH="0e60e394"
9
ARG FA_REPO="https://github.com/Dao-AILab/flash-attention.git"
10
-ARG AITER_BRANCH="eef23c7f"
10
+ARG AITER_BRANCH="9716b1b8"
11
ARG AITER_REPO="https://github.com/ROCm/aiter.git"
12
13
FROM ${BASE_IMAGE} AS base