From 365dfd5f8e00b471b785cba70492c7990671c8ce Mon Sep 17 00:00:00 2001 From: Gao Han Date: Sat, 14 Mar 2026 22:56:43 +0800 Subject: [PATCH] [CI pipeline] Re-enable Diffusion Tensor Parallelism Test in pipeline (#1892) Signed-off-by: Gao Han --- .buildkite/test-merge.yml | 34 +++++++++++++++++----------------- 1 file changed, 17 insertions(+), 17 deletions(-) diff --git a/.buildkite/test-merge.yml b/.buildkite/test-merge.yml index 7fa510716..5479f8ac1 100644 --- a/.buildkite/test-merge.yml +++ b/.buildkite/test-merge.yml @@ -119,23 +119,23 @@ steps: volumes: - "/fsx/hf_cache:/fsx/hf_cache" - # - label: "Diffusion Tensor Parallelism Test" - # timeout_in_minutes: 20 - # depends_on: upload-merge-pipeline - # commands: - # - pytest -s -v tests/e2e/offline_inference/test_zimage_parallelism.py - # agents: - # queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU - # plugins: - # - docker#v5.2.0: - # image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT - # always-pull: true - # propagate-environment: true - # shm-size: "8gb" - # environment: - # - "HF_HOME=/fsx/hf_cache" - # volumes: - # - "/fsx/hf_cache:/fsx/hf_cache" + - label: "Diffusion Tensor Parallelism Test" + timeout_in_minutes: 20 + depends_on: upload-merge-pipeline + commands: + - pytest -s -v tests/e2e/offline_inference/test_zimage_parallelism.py + agents: + queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU + plugins: + - docker#v5.2.0: + image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT + always-pull: true + propagate-environment: true + shm-size: "8gb" + environment: + - "HF_HOME=/fsx/hf_cache" + volumes: + - "/fsx/hf_cache:/fsx/hf_cache" - label: "Diffusion GPU Worker Test" timeout_in_minutes: 20