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 5, 07:15 UTC
[ROCm] [AITER] Revert AITER version to v0.1.10.post3 (#39509)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
TJian committed
Apr 11, 2026 at 00:25 UTC
42c6bb4b7510995b46cf991c2e48cc4322d08b92
1 file changed
+1
-1
docker/Dockerfile.rocm_base
+1
-1
@@ -9,7 +9,7 @@ ARG PYTORCH_AUDIO_BRANCH="v2.9.0"
9
ARG PYTORCH_AUDIO_REPO="https://github.com/pytorch/audio.git"
10
ARG FA_BRANCH="0e60e394"
11
ARG FA_REPO="https://github.com/Dao-AILab/flash-attention.git"
12
-ARG AITER_BRANCH="v0.1.12"
12
+ARG AITER_BRANCH="v0.1.10.post3"
13
ARG AITER_REPO="https://github.com/ROCm/aiter.git"
14
ARG MORI_BRANCH="2d02c6a9"
15
ARG MORI_REPO="https://github.com/ROCm/mori.git"