diff --git a/.buildkite/test-nightly.yml b/.buildkite/test-nightly.yml index 65ad51057..6db22a6a6 100644 --- a/.buildkite/test-nightly.yml +++ b/.buildkite/test-nightly.yml @@ -1276,10 +1276,10 @@ steps: build.pull_request.labels includes "nightly-test" || build.pull_request.labels includes "diffusion-x2v-test" steps: - - label: ":full_moon: Diffusion X2V · Function Test" + - label: ":full_moon: Diffusion X2V · Wan2.2 T2V Function Test" timeout_in_minutes: 90 commands: - - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py tests/e2e/online_serving/test_wan_2_1_vace_expansion.py tests/e2e/online_serving/test_hunyuan_video_15_expansion.py tests/e2e/offline_inference/test_wan22_autoround_w4a16_expansion.py tests/e2e/online_serving/test_ltx2_expansion.py -m "full_model and cuda" --run-level "full_model" + - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "t2v" -m "full_model and cuda" --run-level "full_model" agents: queue: "mithril-h100-pool" plugins: @@ -1314,14 +1314,128 @@ steps: path: /mnt/hf-cache type: DirectoryOrCreate - - label: ":full_moon: Diffusion X2V · Accuracy Test" + - label: ":full_moon: Diffusion X2V · Wan2.2 I2V/TI2V Function Test" + timeout_in_minutes: 90 + commands: + - pytest -s -v tests/e2e/online_serving/test_wan22_expansion.py -k "i2v" -m "full_model and cuda" --run-level "full_model" + agents: + queue: "mithril-h100-pool" + plugins: + - kubernetes: + podSpec: + containers: + - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT + resources: + limits: + nvidia.com/gpu: 2 + volumeMounts: + - name: devshm + mountPath: /dev/shm + - name: hf-cache + mountPath: /root/.cache/huggingface + env: + - name: HF_HOME + value: /root/.cache/huggingface + - name: HF_TOKEN + valueFrom: + secretKeyRef: + name: hf-token-secret + key: token + nodeSelector: + node.kubernetes.io/instance-type: gpu-h100-sxm + volumes: + - name: devshm + emptyDir: + medium: Memory + - name: hf-cache + hostPath: + path: /mnt/hf-cache + type: DirectoryOrCreate + + - label: ":full_moon: Diffusion X2V · Other Function Test" + timeout_in_minutes: 90 + commands: + - pytest -s -v tests/e2e/offline_inference/test_wan22_autoround_w4a16_expansion.py -m "full_model and cuda" --run-level "full_model" + - pytest -s -v tests/e2e/online_serving/test_wan_2_1_vace_expansion.py tests/e2e/online_serving/test_hunyuan_video_15_expansion.py tests/e2e/online_serving/test_ltx2_expansion.py -m "full_model and cuda" --run-level "full_model" + agents: + queue: "mithril-h100-pool" + plugins: + - kubernetes: + podSpec: + containers: + - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$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 + - name: HF_TOKEN + valueFrom: + secretKeyRef: + name: hf-token-secret + key: token + 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: ":full_moon: Diffusion X2V · Wan2.2 Accuracy Test" timeout_in_minutes: 180 commands: - pytest -s -v tests/e2e/accuracy/wan22_i2v/test_wan22_i2v_video_similarity.py -m full_model --run-level full_model + - pytest -s -v tests/e2e/accuracy/test_diffusers_backend_similarity.py -k '2v_matches_diffusers' -m full_model --run-level full_model + agents: + queue: "mithril-h100-pool" + plugins: + - kubernetes: + podSpec: + containers: + - image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/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 + - name: HF_TOKEN + valueFrom: + secretKeyRef: + name: hf-token-secret + key: token + 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: ":full_moon: Diffusion X2V · Other Accuracy Test" + timeout_in_minutes: 180 + commands: - pytest -s -v tests/e2e/accuracy/hunyuanvideo15_t2v/test_hunyuanvideo15_t2v_video_similarity.py -m full_model --run-level full_model - pytest -s -v tests/e2e/accuracy/hunyuanvideo15_i2v/test_hunyuanvideo15_i2v_video_similarity.py -m full_model --run-level full_model - pytest -s -v tests/e2e/accuracy/test_ltx2_3_video_similarity.py -m full_model --run-level full_model - - pytest -s -v tests/e2e/accuracy/test_diffusers_backend_similarity.py -k '2v_matches_diffusers' -m full_model --run-level full_model - pytest -s -v tests/e2e/accuracy/test_video_streaming_output_similarity.py -m full_model --run-level full_model agents: queue: "mithril-h100-pool"