From 8fae682a1feae26f56808153660e9f237d0670bf Mon Sep 17 00:00:00 2001
From: Roger Wang <hey@rogerw.io>
Date: Fri, 5 Dec 2025 23:14:36 +0000
Subject: [PATCH] test

Signed-off-by: Roger Wang <hey@rogerw.io>
---
 .buildkite/pipeline.yml | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/.buildkite/pipeline.yml b/.buildkite/pipeline.yml
index 403675563..129d63872 100644
--- a/.buildkite/pipeline.yml
+++ b/.buildkite/pipeline.yml
@@ -29,3 +29,42 @@ steps:
             - "HF_HOME=/fsx/hf_cache"
           volumes:
             - "/fsx/hf_cache:/fsx/hf_cache"
+  - label: "Large Model Test (H100)"
+    depends_on: image-build
+    soft_fail: false
+    agents:
+      queue: mithril-h100-pool
+    retry:
+      automatic:
+        - exit_status: -1
+          limit: 1
+        - exit_status: -10
+          limit: 1
+    plugins:
+      - kubernetes:
+          podSpec:
+            containers:
+              - image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
+                commands:
+                  - pytest -s -v tests/single_stage/test_diffusion_model.py
+                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