[Hardware][AMD][CI] Fix Spec Decode Eagle test group (#46018)

Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>

.buildkite/test-amd.yaml

@@ -2122,9 +2122,10 @@ steps:
   - pytest -v -s v1/e2e/spec_decode -k "draft_model or no_sync or batch_inference"
 
 - label: Spec Decode Eagle # TBD
-  timeout_in_minutes: 180
+  timeout_in_minutes: 45
   mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
   agent_pool: mi300_1
+  optional: true
   working_dir: "/vllm-workspace/tests"
   source_file_dependencies:
   - vllm/v1/spec_decode/

.buildkite/test_areas/spec_decode.yaml

@@ -12,6 +12,20 @@ steps:
     - tests/v1/e2e/spec_decode/
   commands:
     - pytest -v -s v1/e2e/spec_decode -k "eagle_correctness"
+  mirror:
+    amd:
+      device: mi325_1
+      timeout_in_minutes: 45
+      depends_on:
+      - image-build-amd
+      source_file_dependencies:
+      - vllm/v1/spec_decode/
+      - vllm/v1/worker/gpu/spec_decode/
+      - vllm/model_executor/model_loader/
+      - vllm/v1/sample/
+      - vllm/model_executor/layers/
+      - tests/v1/e2e/spec_decode/
+      - vllm/platforms/rocm.py
 
 - label: Spec Decode Eagle Nightly B200
   key: spec-decode-eagle-nightly-b200

tests/v1/e2e/spec_decode/test_spec_decode.py

@@ -425,7 +425,7 @@ def _run_eagle_correctness(
             if "deepseek" in model_setup[1].lower():
                 m.setenv("VLLM_ROCM_USE_AITER", "1")
                 m.delenv("VLLM_MLA_DISABLE", raising=False)
-                attention_config = {"backend": "TRITON_MLA"}
+                attention_config = {"backend": "ROCM_AITER_MLA"}
             else:
                 m.setenv("VLLM_ROCM_USE_AITER", "1")