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, 19:30 UTC
[Build/CI] Fixing Docker Hub quota issue. (#7043)
Alexei-V-Ivanov-AMD committed
Aug 1, 2024 at 13:07 UTC
a72a424b3eac43a26d2214c0f2a7f91cc59f2f84
1 file changed
+1
-1
.buildkite/run-amd-test.sh
+1
-1
@@ -56,7 +56,7 @@ 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}"
59
+image_name="rocm/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}
62