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, 20:45 UTC
[Build/CI] Update run-amd-test.sh. Enable Docker Hub login. (#6711)
Alexei-V-Ivanov-AMD committed
Jul 24, 2024 at 07:01 UTC
b5708117060460fcc6ba6f58e0669d3c46d6339e
1 file changed
+1
.buildkite/run-amd-test.sh
+1
@@ -55,6 +55,7 @@ while true; do
55
done
56
57
echo "--- Pulling container"
58
+docker login registry-1.docker.io -u alexeivivanovamd -p ${DH_TOKEN}
59
image_name="rocmshared/vllm-ci:${BUILDKITE_COMMIT}"
60
container_name="rocm_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | head -c 10; echo)"
61
docker pull ${image_name}