[ROCm][CI] Fix ROCm GPT-OSS Eval test group (#36179)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>

.buildkite/test-amd.yaml

@@ -1640,7 +1640,7 @@ steps:
   - vllm/v1/attention/backends/flashinfer.py
   commands:
   - uv pip install --system 'gpt-oss[eval]==0.0.5'
-    - VLLM_ROCM_USE_AITER_MHA=0 VLLM_ROCM_USE_AITER=1 VLLM_USE_AITER_UNIFIED_ATTENTION=1 pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py --model openai/gpt-oss-20b --metric 0.58
+  - pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-gfx942.txt
 
 ##### EPLB Accuracy Tests #####
 - label: DeepSeek V2-Lite Accuracy
@@ -3297,7 +3297,7 @@ steps:
   - vllm/v1/attention/backends/flashinfer.py
   commands:
   - uv pip install --system 'gpt-oss[eval]==0.0.5'
-    - VLLM_ROCM_USE_AITER_MHA=0 VLLM_ROCM_USE_AITER=1 VLLM_USE_AITER_UNIFIED_ATTENTION=1 pytest -s -v tests/evals/gpt_oss/test_gpqa_correctness.py --model openai/gpt-oss-20b --metric 0.58
+  - pytest -s -v evals/gpt_oss/test_gpqa_correctness.py --config-list-file=configs/models-gfx950.txt
 
 ##### EPLB Accuracy Tests #####
 - label: DeepSeek V2-Lite Accuracy

tests/evals/gpt_oss/configs/gpt-oss-20b-rocm-baseline.yaml

@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: openai/gpt-oss-20b
+metric_threshold: 0.568
+reasoning_effort: low
+server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN"

tests/evals/gpt_oss/configs/models-gfx942.txt

@@ -0,0 +1,3 @@
+# GFX942 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-rocm-baseline.yaml

tests/evals/gpt_oss/configs/models-gfx950.txt

@@ -0,0 +1,3 @@
+# GFX950 model configurations for GPQA evaluation
+# Tests different environment variable combinations
+gpt-oss-20b-rocm-baseline.yaml