From e90b608c42f60b03c20f57fabe22ec0d3cacd76c Mon Sep 17 00:00:00 2001 From: "Kevin H. Luu" Date: Tue, 1 Sep 2026 15:29:33 -0700 Subject: [PATCH] [CI] Split nightly MTP acceptance tests (#52353) Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com> --- .buildkite/test_areas/spec_decode.yaml | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/.buildkite/test_areas/spec_decode.yaml b/.buildkite/test_areas/spec_decode.yaml index 8592881750..47255d041d 100644 --- a/.buildkite/test_areas/spec_decode.yaml +++ b/.buildkite/test_areas/spec_decode.yaml @@ -349,13 +349,19 @@ steps: - label: ":nvidia: (H200 MIG 35GB) Spec Decode AL MTP + Other Acceptance Nightly" key: spec-decode-mtp-other-acceptance-nightly - timeout_in_minutes: 60 + timeout_in_minutes: 35 device: h200_35gb optional: true + parallelism: 3 source_file_dependencies: - vllm/v1/spec_decode/ - vllm/v1/worker/gpu/spec_decode/ - tests/v1/e2e/spec_decode/conftest.py - tests/v1/e2e/spec_decode/ commands: - - pytest -v -s v1/e2e/spec_decode/acceptance_rates/mtp_other/ + # Each Gemma4 parametrization is an indivisible ~23m floor. Keep them in + # separate shards and put the remaining tests in shard 0, where new tests + # land by default. + - test "$$BUILDKITE_PARALLEL_JOB" != "0" || pytest -v -s v1/e2e/spec_decode/acceptance_rates/mtp_other/ --deselect "tests/v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[False]" --deselect "tests/v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[True]" + - test "$$BUILDKITE_PARALLEL_JOB" != "1" || pytest -v -s "v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[False]" + - test "$$BUILDKITE_PARALLEL_JOB" != "2" || pytest -v -s "v1/e2e/spec_decode/acceptance_rates/mtp_other/test_mtp.py::test_gemma4_mtp_acceptance_lengths[True]"