From 5a58a1aac02f3be1d72409277874037fe21f67d9 Mon Sep 17 00:00:00 2001
From: wangyu <53896905+yenuo26@users.noreply.github.com>
Date: Mon, 23 Mar 2026 19:29:44 +0800
Subject: [PATCH] [CI] Update Diffusion Model Test Configuration for Nightly
 Builds (#2086)

Signed-off-by: yenuo26 <410167048@qq.com>
Signed-off-by: wangyu <53896905+yenuo26@users.noreply.github.com>
---
 .buildkite/test-merge.yml   | 24 ------------------------
 .buildkite/test-nightly.yml | 22 ++++++++++++++++++++++
 2 files changed, 22 insertions(+), 24 deletions(-)

diff --git a/.buildkite/test-merge.yml b/.buildkite/test-merge.yml
index 2eb68941a..b606648c7 100644
--- a/.buildkite/test-merge.yml
+++ b/.buildkite/test-merge.yml
@@ -126,30 +126,6 @@ steps:
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
 
-  - label: "Diffusion Model Test with L4"
-    timeout_in_minutes: 60
-    depends_on: upload-merge-pipeline
-    # This should run nightly, but moving to the merge pipeline for testing
-    #depends_on: upload-nightly-pipeline
-    # if: build.env("NIGHTLY") == "1"
-    #
-    commands:
-      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
-      - pytest -s -v tests/e2e/online_serving/test_*_expansion.py -m "advanced_model and diffusion and L4" --run-level "advanced_model"
-    agents:
-      queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
-    plugins:
-      - docker#v5.2.0:
-          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
-          always-pull: true
-          propagate-environment: true
-          shm-size: "8gb"
-          environment:
-            - "HF_HOME=/fsx/hf_cache"
-            - "HF_TOKEN"
-          volumes:
-            - "/fsx/hf_cache:/fsx/hf_cache"
-
   - label: "Diffusion Tensor Parallelism Test"
     timeout_in_minutes: 20
     depends_on: upload-merge-pipeline
diff --git a/.buildkite/test-nightly.yml b/.buildkite/test-nightly.yml
index 6a6123f24..2ed96d382 100644
--- a/.buildkite/test-nightly.yml
+++ b/.buildkite/test-nightly.yml
@@ -111,6 +111,28 @@ steps:
                   path: /mnt/hf-cache
                   type: DirectoryOrCreate
 
+  - label: ":full_moon: Diffusion Model Test with L4"
+    timeout_in_minutes: 60
+    depends_on: upload-nightly-pipeline
+    if: build.env("NIGHTLY") == "1"
+    commands:
+      - export VLLM_WORKER_MULTIPROC_METHOD=spawn
+      - pytest -s -v tests/e2e/online_serving/test_*_expansion.py -m "advanced_model and diffusion and L4" --run-level "advanced_model"
+    agents:
+      queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
+    plugins:
+      - docker#v5.2.0:
+          image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+          always-pull: true
+          propagate-environment: true
+          shm-size: "8gb"
+          environment:
+            - "HF_HOME=/fsx/hf_cache"
+            - "HF_TOKEN"
+          volumes:
+            - "/fsx/hf_cache:/fsx/hf_cache"
+
+
   - label: ":full_moon: Documentation Example Code Test with H100"
     timeout_in_minutes: 60
     depends_on: upload-nightly-pipeline