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 8, 15:15 UTC
[ROCm] update triton branch to support gpt-oss models for gfx11xx devices (#34032)
Signed-off-by: Hongxia Yang <hongxia.yang@amd.com>
Hongxia Yang committed
Feb 9, 2026 at 14:36 UTC
4d3965096164328451538988824d72ab03593c04
1 file changed
+1
-1
docker/Dockerfile.rocm_base
+1
-1
@@ -1,5 +1,5 @@
1
ARG BASE_IMAGE=rocm/dev-ubuntu-22.04:7.0-complete
2
-ARG TRITON_BRANCH="57c693b6"
2
+ARG TRITON_BRANCH="f332c492"
3
ARG TRITON_REPO="https://github.com/ROCm/triton.git"
4
ARG PYTORCH_BRANCH="89075173"
5
ARG PYTORCH_REPO="https://github.com/ROCm/pytorch.git"