[CI][ROCm] Add gpt-oss w4a8 in CI (#38292)

Signed-off-by: Bowen Bao <bowenbao@amd.com>

tests/evals/gpt_oss/configs/gpt-oss-20b-rocm-mxfp4-fp8.yaml

+# SPDX-License-Identifier: Apache-2.0
+# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
+model_name: amd/gpt-oss-20b-MoE-Quant-W-MXFP4-A-FP8-KV-FP8
+metric_threshold: 0.568
+reasoning_effort: low
+server_args: "--attention-backend ROCM_AITER_UNIFIED_ATTN"
+env:
+  VLLM_ROCM_USE_AITER: "1"
\ No newline at end of file

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

 # GFX950 model configurations for GPQA evaluation
 # Tests different environment variable combinations
-gpt-oss-20b-rocm-baseline.yaml
+gpt-oss-20b-rocm-baseline.yaml
\ No newline at end of file
+gpt-oss-20b-rocm-mxfp4-fp8.yaml
\ No newline at end of file