anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[CI] Temporarily remove slow tests. (#1143)

Browse Source 
Signed-off-by: Alicia <115451386+congw729@users.noreply.github.com>
Signed-off-by: princepride <wangzhipeng628@gmail.com>
Co-authored-by: princepride <wangzhipeng628@gmail.com>
This commit is contained in:
Aliciaandprincepride authored and GitHub committed 2026-02-02 20:36:56 +08:00
1 parent dc6177520e
commit 47b11c6b13
4 files changed
+77 -77
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/pipeline.yml
+71 -71
View File
@@ -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
tests/e2e/offline_inference/stage_configs/bagel_mooncake_ci.yaml
+2 -2
View File
@@ -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
tests/e2e/offline_inference/stage_configs/bagel_sharedmemory_ci.yaml
+2 -2
View File
@@ -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
tests/e2e/offline_inference/test_bagel_text2img.py
+2 -2
View File
@@ -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)