From 47b11c6b130ca70aee5f434c069824b5341ae3b5 Mon Sep 17 00:00:00 2001 From: Alicia <115451386+congw729@users.noreply.github.com> Date: Mon, 2 Feb 2026 20:36:56 +0800 Subject: [PATCH] [CI] Temporarily remove slow tests. (#1143) Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com> Signed-off-by: princepride Co-authored-by: princepride --- .buildkite/pipeline.yml | 142 +++++++++--------- .../stage_configs/bagel_mooncake_ci.yaml | 4 +- .../stage_configs/bagel_sharedmemory_ci.yaml | 4 +- .../offline_inference/test_bagel_text2img.py | 4 +- 4 files changed, 77 insertions(+), 77 deletions(-) diff --git a/.buildkite/pipeline.yml b/.buildkite/pipeline.yml index f7f3e4b05..402e62518 100644 --- a/.buildkite/pipeline.yml +++ b/.buildkite/pipeline.yml @@ -233,43 +233,43 @@ steps: volumes: - "/fsx/hf_cache:/fsx/hf_cache" - - label: "Omni Model Test with H100" - timeout_in_minutes: 30 - depends_on: image-build - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - export VLLM_TEST_CLEAN_GPU_MEMORY="1" - - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py - - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py - - pytest -s -v tests/e2e/online_serving/test_async_omni.py - agents: - queue: "mithril-h100-pool" - plugins: - - kubernetes: - podSpec: - containers: - - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT - resources: - limits: - nvidia.com/gpu: 2 - volumeMounts: - - name: devshm - mountPath: /dev/shm - - name: hf-cache - mountPath: /root/.cache/huggingface - env: - - name: HF_HOME - value: /root/.cache/huggingface - nodeSelector: - node.kubernetes.io/instance-type: gpu-h100-sxm - volumes: - - name: devshm - emptyDir: - medium: Memory - - name: hf-cache - hostPath: - path: /mnt/hf-cache - type: DirectoryOrCreate + # - label: "Omni Model Test with H100" + # timeout_in_minutes: 30 + # depends_on: image-build + # commands: + # - export VLLM_WORKER_MULTIPROC_METHOD=spawn + # - export VLLM_TEST_CLEAN_GPU_MEMORY="1" + # - pytest -s -v tests/e2e/offline_inference/test_qwen3_omni.py + # - pytest -s -v tests/e2e/online_serving/test_qwen3_omni.py + # - pytest -s -v tests/e2e/online_serving/test_async_omni.py + # agents: + # queue: "mithril-h100-pool" + # plugins: + # - kubernetes: + # podSpec: + # containers: + # - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT + # resources: + # limits: + # nvidia.com/gpu: 2 + # volumeMounts: + # - name: devshm + # mountPath: /dev/shm + # - name: hf-cache + # mountPath: /root/.cache/huggingface + # env: + # - name: HF_HOME + # value: /root/.cache/huggingface + # nodeSelector: + # node.kubernetes.io/instance-type: gpu-h100-sxm + # volumes: + # - name: devshm + # emptyDir: + # medium: Memory + # - name: hf-cache + # hostPath: + # path: /mnt/hf-cache + # type: DirectoryOrCreate - label: "Diffusion Image Edit Test with H100 (1 GPU)" timeout_in_minutes: 20 @@ -306,37 +306,37 @@ steps: path: /mnt/hf-cache type: DirectoryOrCreate - - label: "Bagel Text2Img Model Test with H100" - timeout_in_minutes: 30 - depends_on: image-build - commands: - - export VLLM_WORKER_MULTIPROC_METHOD=spawn - - pytest -s -v tests/e2e/offline_inference/test_bagel_text2img.py - agents: - queue: "mithril-h100-pool" - plugins: - - kubernetes: - podSpec: - containers: - - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT - resources: - limits: - nvidia.com/gpu: 1 - volumeMounts: - - name: devshm - mountPath: /dev/shm - - name: hf-cache - mountPath: /root/.cache/huggingface - env: - - name: HF_HOME - value: /root/.cache/huggingface - nodeSelector: - node.kubernetes.io/instance-type: gpu-h100-sxm - volumes: - - name: devshm - emptyDir: - medium: Memory - - name: hf-cache - hostPath: - path: /mnt/hf-cache - type: DirectoryOrCreate + # - label: "Bagel Text2Img Model Test with H100" + # timeout_in_minutes: 30 + # depends_on: image-build + # commands: + # - export VLLM_WORKER_MULTIPROC_METHOD=spawn + # - pytest -s -v tests/e2e/offline_inference/test_bagel_text2img.py + # agents: + # queue: "mithril-h100-pool" + # plugins: + # - kubernetes: + # podSpec: + # containers: + # - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT + # resources: + # limits: + # nvidia.com/gpu: 1 + # volumeMounts: + # - name: devshm + # mountPath: /dev/shm + # - name: hf-cache + # mountPath: /root/.cache/huggingface + # env: + # - name: HF_HOME + # value: /root/.cache/huggingface + # nodeSelector: + # node.kubernetes.io/instance-type: gpu-h100-sxm + # volumes: + # - name: devshm + # emptyDir: + # medium: Memory + # - name: hf-cache + # hostPath: + # path: /mnt/hf-cache + # type: DirectoryOrCreate diff --git a/tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml b/tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml index 4c6a67e8b..8c170dffd 100644 --- a/tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml +++ b/tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml @@ -12,7 +12,7 @@ stage_args: model_arch: BagelForConditionalGeneration worker_type: ar scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler - gpu_memory_utilization: 0.60 + gpu_memory_utilization: 0.35 enforce_eager: true trust_remote_code: true engine_output_type: text @@ -44,7 +44,7 @@ stage_args: max_batch_size: 1 engine_args: model_stage: dit - gpu_memory_utilization: 0.4 + gpu_memory_utilization: 0.55 enforce_eager: true trust_remote_code: true engine_output_type: image diff --git a/tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml b/tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml index 67ff7309f..ef605a3a3 100644 --- a/tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml +++ b/tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml @@ -12,7 +12,7 @@ stage_args: model_arch: BagelForConditionalGeneration worker_type: ar scheduler_cls: vllm_omni.core.sched.omni_ar_scheduler.OmniARScheduler - gpu_memory_utilization: 0.65 + gpu_memory_utilization: 0.35 enforce_eager: true trust_remote_code: true engine_output_type: text @@ -43,7 +43,7 @@ stage_args: max_batch_size: 1 engine_args: model_stage: dit - gpu_memory_utilization: 0.4 + gpu_memory_utilization: 0.55 enforce_eager: true trust_remote_code: true engine_output_type: image diff --git a/tests/e2e/offline_inference/test_bagel_text2img.py b/tests/e2e/offline_inference/test_bagel_text2img.py index 777af52a7..9aef47a74 100644 --- a/tests/e2e/offline_inference/test_bagel_text2img.py +++ b/tests/e2e/offline_inference/test_bagel_text2img.py @@ -161,7 +161,7 @@ def _generate_bagel_image(omni: Omni, prompt: str = DEFAULT_PROMPT) -> Image.Ima def test_bagel_text2img_shared_memory_connector(): """Test Bagel text2img with shared memory connector.""" config_path = str(Path(__file__).parent / "stage_configs" / "bagel_sharedmemory_ci.yaml") - omni = Omni(model="ByteDance-Seed/BAGEL-7B-MoT", stage_configs_path=config_path) + omni = Omni(model="ByteDance-Seed/BAGEL-7B-MoT", stage_configs_path=config_path, stage_init_timeout=300) try: generated_image = _generate_bagel_image(omni) @@ -288,7 +288,7 @@ def test_bagel_text2img_mooncake_connector(): http_port=MOONCAKE_HTTP_PORT, ) - omni = Omni(model="ByteDance-Seed/BAGEL-7B-MoT", stage_configs_path=temp_config_file) + omni = Omni(model="ByteDance-Seed/BAGEL-7B-MoT", stage_configs_path=temp_config_file, stage_init_timeout=300) generated_image = _generate_bagel_image(omni) _validate_pixels(generated_image)