From b63e35ab4ffae2f78b556150943ec0e08a444030 Mon Sep 17 00:00:00 2001 From: andyluo7 <43718156+andyluo7@users.noreply.github.com> Date: Sun, 27 Sep 2026 14:11:05 +0800 Subject: [PATCH] ci: extend AMD Z-Image cold-start timeout (#8195) Signed-off-by: andyluo7 Co-authored-by: Alicia <115451386+congw729@users.noreply.github.com> --- .buildkite/amd/test-amd-merge.yml | 4 +++- tests/buildkite/test_amd_pipeline.py | 7 +++++++ 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/.buildkite/amd/test-amd-merge.yml b/.buildkite/amd/test-amd-merge.yml index 6ee36de48..1e3e852e9 100644 --- a/.buildkite/amd/test-amd-merge.yml +++ b/.buildkite/amd/test-amd-merge.yml @@ -138,7 +138,9 @@ steps: mirror_hardwares: [amdproduction] grade: Blocking commands: - - timeout 30m pytest -s -v tests/e2e/offline_inference/test_z_image.py + # A cold Z-Image run spends about six minutes loading weights before + # the first-request AITER compilation, which can itself exceed 23m. + - timeout 55m pytest -s -v tests/e2e/offline_inference/test_z_image.py - label: "Diffusion GPU Worker Test" agent_pool: mi300_2 diff --git a/tests/buildkite/test_amd_pipeline.py b/tests/buildkite/test_amd_pipeline.py index 36df7ac3e..e7c428dd1 100644 --- a/tests/buildkite/test_amd_pipeline.py +++ b/tests/buildkite/test_amd_pipeline.py @@ -67,6 +67,13 @@ def test_ready_diffusion_cpu_suite_is_sharded() -> None: assert "--shard-id=$$BUILDKITE_PARALLEL_JOB" in pytest_command +def test_z_image_merge_timeout_covers_cold_aiter_compile() -> None: + step = _find_step("Diffusion Model Test") + pytest_command = next(command for command in step["commands"] if "test_z_image.py" in command) + + assert split(pytest_command)[:2] == ["timeout", "55m"] + + def test_cosyvoice_ready_smoke_uses_sdpa() -> None: step = _find_step("CosyVoice3-TTS E2E Smoke (SDPA)", AMD_READY_PIPELINE)