diff --git a/.buildkite/common/ci_source_file_dependencies.yml b/.buildkite/common/ci_source_file_dependencies.yml index 5dfbf8da4..99bbffa75 100644 --- a/.buildkite/common/ci_source_file_dependencies.yml +++ b/.buildkite/common/ci_source_file_dependencies.yml @@ -453,6 +453,7 @@ source_file_dependencies: - *lingbot_video - *lingbot_world - tests/e2e/online_serving/test_lingbot_video.py + - tests/e2e/online_serving/test_lingbot_video_expansion.py - tests/e2e/online_serving/test_lingbot_video_moe.py - tests/e2e/offline_inference/test_lingbot_world_v2.py diff --git a/.buildkite/cuda/test-merge.yml b/.buildkite/cuda/test-merge.yml index 87d4c5362..86e7a7a35 100644 --- a/.buildkite/cuda/test-merge.yml +++ b/.buildkite/cuda/test-merge.yml @@ -163,6 +163,16 @@ steps: " mirror_hardwares: h100_1 + - label: "Diffusion · LingBot-Video Test" + source_file_dependencies: diffusion_lingbot_function + commands: + - | + timeout 40m bash -c " + export VLLM_IMAGE_FETCH_TIMEOUT=60 + pytest -s -v tests/e2e/online_serving/test_lingbot_video.py -m 'advanced_model and cuda and diffusion' --run-level 'advanced_model' + " + mirror_hardwares: h100_1 + - label: "Diffusion · MiniMax-H3 L3 DLO DP2 and FastH3" source_file_dependencies: diffusion_minimax_h3_function # Keep four server lifecycles in one Buildkite job, but never in one diff --git a/.buildkite/cuda/test-nightly.yml b/.buildkite/cuda/test-nightly.yml index adc94f9e9..843b8d9a3 100644 --- a/.buildkite/cuda/test-nightly.yml +++ b/.buildkite/cuda/test-nightly.yml @@ -349,7 +349,7 @@ steps: commands: - >- pytest -s -v - tests/e2e/online_serving/test_lingbot_video.py + tests/e2e/online_serving/test_lingbot_video_expansion.py tests/e2e/online_serving/test_lingbot_video_moe.py tests/e2e/offline_inference/test_lingbot_world_v2.py -m "full_model and diffusion and H100 and B200 and cards_1" diff --git a/.buildkite/cuda/test-ready.yml b/.buildkite/cuda/test-ready.yml index 04e5d07b0..771554c0f 100644 --- a/.buildkite/cuda/test-ready.yml +++ b/.buildkite/cuda/test-ready.yml @@ -248,3 +248,13 @@ steps: pytest -s -v tests/e2e/online_serving/test_hunyuan_video_15_expansion.py -m 'core_model and diffusion' --run-level 'core_model' " mirror_hardwares: h100_1 + + - label: "Diffusion · LingBot-Video Test" + source_file_dependencies: diffusion_lingbot_function + commands: + - | + timeout 40m bash -c " + export VLLM_IMAGE_FETCH_TIMEOUT=60 + pytest -s -v tests/e2e/online_serving/test_lingbot_video.py -m 'core_model and cuda' --run-level 'core_model' + " + mirror_hardwares: h100_1 diff --git a/tests/e2e/online_serving/test_lingbot_video.py b/tests/e2e/online_serving/test_lingbot_video.py index e6f275bb9..0da9c4dab 100644 --- a/tests/e2e/online_serving/test_lingbot_video.py +++ b/tests/e2e/online_serving/test_lingbot_video.py @@ -1,7 +1,19 @@ # SPDX-License-Identifier: Apache-2.0 # SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project -"""Online serving smoke coverage for the dense LingBot-Video checkpoint.""" +""" +Online serving smoke for ``robbyant/lingbot-video-dense-1.3b``. + +``test_text_to_image_001`` and ``test_video_generation_modes_001`` are the +baseline T2I / T2V+TI2V cases (``core_model`` + ``advanced_model``) shared by +ready (L2) and merge (L3). Heavier MoE and World coverage stays on +``full_model`` in ``test_lingbot_video_moe.py`` / ``test_lingbot_world_v2.py``. + +From ``tests/``:: + + pytest -s -v e2e/online_serving/test_lingbot_video.py -m "core_model and diffusion" --run-level=core_model + pytest -s -v e2e/online_serving/test_lingbot_video.py -m "advanced_model and diffusion" --run-level=advanced_model +""" import json import os @@ -41,7 +53,8 @@ def _get_diffusion_feature_cases(model: str): ] -@pytest.mark.full_model +@pytest.mark.core_model +@pytest.mark.advanced_model @pytest.mark.diffusion @pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True) def test_text_to_image_001(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None: @@ -63,7 +76,8 @@ def test_text_to_image_001(omni_server: OmniServer, openai_client: OpenAIClientH ) -@pytest.mark.full_model +@pytest.mark.core_model +@pytest.mark.advanced_model @pytest.mark.diffusion @pytest.mark.parametrize("omni_server", _get_diffusion_feature_cases(MODEL), indirect=True) def test_video_generation_modes_001(omni_server: OmniServer, openai_client: OpenAIClientHandler) -> None: diff --git a/tests/e2e/online_serving/test_lingbot_video_expansion.py b/tests/e2e/online_serving/test_lingbot_video_expansion.py index 4a411ddcf..74c7c143b 100644 --- a/tests/e2e/online_serving/test_lingbot_video_expansion.py +++ b/tests/e2e/online_serving/test_lingbot_video_expansion.py @@ -4,9 +4,9 @@ """ L4 expansion coverage for ``robbyant/lingbot-video-dense-1.3b``. -This file remains dense-only. Basic T2I/T2V/TI2V serving for both dense and MoE -checkpoints is covered by ``test_lingbot_video.py`` and -``test_lingbot_video_moe.py``. Distributed feature rows belong in follow-up +This file remains dense-only. Baseline T2I/T2V/TI2V for the dense checkpoint +lives in ``test_lingbot_video.py`` (L2/L3). MoE smoke stays in +``test_lingbot_video_moe.py`` (L4). Distributed feature rows belong in follow-up PRs. """