diff --git a/.buildkite/run-amd-test.sh b/.buildkite/run-amd-test.sh index 5a72f9037c32..706737e70d04 100755 --- a/.buildkite/run-amd-test.sh +++ b/.buildkite/run-amd-test.sh @@ -57,7 +57,7 @@ while true; do done echo "--- Pulling container" -image_name="rocm/vllm-ci:${BUILDKITE_COMMIT}" +image_name="rocm/vllm-ci-private:${BUILDKITE_COMMIT}" container_name="rocm_${BUILDKITE_COMMIT}_$(tr -dc A-Za-z0-9 < /dev/urandom | head -c 10; echo)" docker pull "${image_name}" diff --git a/.buildkite/test-template.j2 b/.buildkite/test-template.j2 index 573675d67f86..3f157a9f153e 100644 --- a/.buildkite/test-template.j2 +++ b/.buildkite/test-template.j2 @@ -1,5 +1,5 @@ {% set docker_image = "public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT" %} -{% set docker_image_amd = "rocm/vllm-ci:$BUILDKITE_COMMIT" %} +{% set docker_image_amd = "rocm/vllm-ci-private:$BUILDKITE_COMMIT" %} {% set default_working_dir = "vllm/tests" %} {% set hf_home = "/root/.cache/huggingface" %} @@ -7,7 +7,7 @@ steps: - label: ":docker: build image" depends_on: ~ commands: - - "docker build --build-arg max_jobs=16 --tag {{ docker_image_amd }} -f Dockerfile.rocm --target test --progress plain ." + - "docker build --build-arg max_jobs=16 --tag {{ docker_image_amd }} -f Dockerfile.rocm --build-arg ARG_PYTORCH_ROCM_ARCH='gfx90a;gfx942' --target test --progress plain ." - "docker push {{ docker_image_amd }}" key: "amd-build" env: @@ -27,7 +27,15 @@ steps: depends_on: - "amd-build" agents: +{% if step.amd_gpus and step.amd_gpus==8%} queue: amd_gpu +{% elif step.amd_gpus and step.amd_gpus==4%} + queue: amd_gpu +{% elif step.amd_gpus and step.amd_gpus==2%} + queue: amd_gpu +{% else%} + queue: amd_gpu_1_osci_v2 +{% endif%} commands: - bash .buildkite/run-amd-test.sh "cd {{ (step.working_dir or default_working_dir) | safe }} ; {{ step.command or (step.commands | join(" && ")) | safe }}" env: