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 15, 14:45 UTC
[CI]Fix hpu docker and numpy version for CI (#16355)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Chendi.Xue committed
Apr 9, 2025 at 12:52 UTC
566f10a9293425483ac47892e2a6cd4960177a59
2 files changed
+2
-1
docker/Dockerfile.hpu
+1
-1
@@ -1,4 +1,4 @@
1
-FROM vault.habana.ai/gaudi-docker/1.19.1/ubuntu22.04/habanalabs/pytorch-installer-2.5.1:latest
1
+FROM vault.habana.ai/gaudi-docker/1.20.1/ubuntu22.04/habanalabs/pytorch-installer-2.6.0:latest
2
3
COPY ./ /workspace/vllm
4
requirements/hpu.txt
+1
@@ -5,6 +5,7 @@
5
ray
6
triton==3.1.0
7
pandas
8
+numpy==1.26.4
9
tabulate
10
setuptools>=61
11
setuptools-scm>=8