From dced2907693e3d6bf9eb7168d0a8fecf1cd22dca Mon Sep 17 00:00:00 2001
From: Matt <156021403+mawong-amd@users.noreply.github.com>
Date: Sat, 20 Jun 2026 02:04:35 -0500
Subject: [PATCH] [Hardware][AMD][CI] Fix e2e core test group (#46024)

Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
---
 .buildkite/test-amd.yaml                       | 15 +--------------
 .buildkite/test_areas/engine.yaml              | 10 ++++++++++
 tests/v1/e2e/general/test_cascade_attention.py |  7 +++++++
 3 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/.buildkite/test-amd.yaml b/.buildkite/test-amd.yaml
index a7f3d67e79f..5550c0a0c18 100644
--- a/.buildkite/test-amd.yaml
+++ b/.buildkite/test-amd.yaml
@@ -647,7 +647,7 @@ steps:
   - pytest -v -s v1/cudagraph/test_cudagraph_mode.py
 
 - label: e2e Core (1 GPU) # TBD
-  timeout_in_minutes: 180
+  timeout_in_minutes: 35
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
   agent_pool: mi250_1
   optional: true
@@ -2075,19 +2075,6 @@ steps:
   - export VLLM_ALLOW_INSECURE_SERIALIZATION=1
   - pytest -v -s v1/spec_decode/test_acceptance_length.py -m slow_test
 
-- label: e2e Core (1 GPU) # TBD
-  timeout_in_minutes: 180
-  mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
-  agent_pool: mi300_1
-  optional: true
-  working_dir: "/vllm-workspace/tests"
-  source_file_dependencies:
-  - vllm/v1/
-  - tests/v1/e2e/
-  - vllm/platforms/rocm.py
-  commands:
-  - pytest -v -s v1/e2e/general --ignore v1/e2e/general/test_async_scheduling.py
-
 - label: e2e Scheduling (1 GPU) # TBD
   timeout_in_minutes: 180
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
diff --git a/.buildkite/test_areas/engine.yaml b/.buildkite/test_areas/engine.yaml
index 67ed8e377ae..98c8231831d 100644
--- a/.buildkite/test_areas/engine.yaml
+++ b/.buildkite/test_areas/engine.yaml
@@ -74,6 +74,16 @@ steps:
     - tests/v1/e2e/general/
   commands:
     - pytest -v -s v1/e2e/general --ignore v1/e2e/general/test_async_scheduling.py
+  mirror:
+    amd:
+      device: mi250_1
+      timeout_in_minutes: 35
+      depends_on:
+      - image-build-amd
+      source_file_dependencies:
+      - vllm/v1/
+      - tests/v1/e2e/general/
+      - vllm/platforms/rocm.py
 
 - label: V1 e2e (2 GPUs)
   key: v1-e2e-2-gpus
diff --git a/tests/v1/e2e/general/test_cascade_attention.py b/tests/v1/e2e/general/test_cascade_attention.py
index be889b38690..251746271de 100644
--- a/tests/v1/e2e/general/test_cascade_attention.py
+++ b/tests/v1/e2e/general/test_cascade_attention.py
@@ -4,9 +4,16 @@
 import pytest
 
 from vllm import LLM, SamplingParams
+from vllm.platforms import current_platform
 
 from ....utils import create_new_process_for_each_test
 
+if current_platform.is_rocm():
+    pytest.skip(
+        "Cascade attention backends FLASH_ATTN and FLASHINFER are notsupported on ROCm",
+        allow_module_level=True,
+    )
+
 
 @create_new_process_for_each_test()
 @pytest.mark.parametrize("attn_backend", ["FLASH_ATTN", "FLASHINFER"])