[ci][amd] fix basic models extra init test (#28676)

Signed-off-by: Bradley Davis <bradleyhd@meta.com>
This commit is contained in:
Bradley D 2025-11-13 18:44:36 -08:00 committed by GitHub
parent 622e6106a9
commit b39a5026eb
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -59,7 +59,7 @@ while true; do
fi
done
echo "--- Pulling container"
echo "--- Pulling container"
image_name="rocm/vllm-ci:${BUILDKITE_COMMIT}"
container_name="rocm_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | head -c 10; echo)"
docker pull "${image_name}"
@ -177,13 +177,13 @@ if [[ -z "$render_gid" ]]; then
exit 1
fi
# check if the command contains shard flag, we will run all shards in parallel because the host have 8 GPUs.
# check if the command contains shard flag, we will run all shards in parallel because the host have 8 GPUs.
if [[ $commands == *"--shard-id="* ]]; then
# assign job count as the number of shards used
commands=${commands//"--num-shards= "/"--num-shards=${PARALLEL_JOB_COUNT} "}
# assign job count as the number of shards used
commands=$(echo "$commands" | sed -E "s/--num-shards[[:blank:]]*=[[:blank:]]*[0-9]*/--num-shards=${PARALLEL_JOB_COUNT} /g" | sed 's/ \\ / /g')
for GPU in $(seq 0 $(($PARALLEL_JOB_COUNT-1))); do
# assign shard-id for each shard
commands_gpu=${commands//"--shard-id= "/"--shard-id=${GPU} "}
commands_gpu=$(echo "$commands" | sed -E "s/--shard-id[[:blank:]]*=[[:blank:]]*[0-9]*/--shard-id=${GPU} /g" | sed 's/ \\ / /g')
echo "Shard ${GPU} commands:$commands_gpu"
echo "Render devices: $BUILDKITE_AGENT_META_DATA_RENDER_DEVICES"
docker run \