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 16, 02:00 UTC
[ci/build] update nightly torch for gh200 test (#12270)
Signed-off-by: youkaichao <youkaichao@gmail.com>
youkaichao committed
Jan 21, 2025 at 23:03 UTC
3aec49e56f60c8ccafe108a8922c731e235a8fcc
1 file changed
+1
-1
Dockerfile
+1
-1
@@ -52,7 +52,7 @@ WORKDIR /workspace
52
# after this step
53
RUN --mount=type=cache,target=/root/.cache/pip \
54
if [ "$TARGETPLATFORM" = "linux/arm64" ]; then \
55
- python3 -m pip install --index-url https://download.pytorch.org/whl/nightly/cu124 "torch==2.6.0.dev20241210+cu124" "torchvision==0.22.0.dev20241215"; \
55
+ python3 -m pip install --index-url https://download.pytorch.org/whl/nightly/cu126 "torch==2.7.0.dev20250121+cu126" "torchvision==0.22.0.dev20250121"; \
56
fi
57
58
COPY requirements-common.txt requirements-common.txt