[ROCm][CI] Add AMD job for DeepSeek-V4.1 Mono Decode Numerics (#61720)

Signed-off-by: aarushjain29 <aarushi.jain2@amd.com>

.buildkite/test-amd.yaml

@@ -4918,6 +4918,23 @@ steps:
   - amd-smi
   - VLLM_ROCM_USE_AITER=1 VLLM_ROCM_USE_AITER_MOE=1 VLLM_ROCM_USE_AITER_FUSION_SHARED_EXPERTS=0 pytest -v -s kernels/moe/test_mori_moe.py
 
+- label: ":amd: (MI355) DeepSeek-V4.1 Mono Decode Numerics"
+  timeout_in_minutes: 40
+  mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
+  dind: false
+  agent_pool: mi355_4
+  num_gpus: 4
+  optional: true
+  working_dir: "/vllm-workspace/"
+  source_file_dependencies:
+  - docker/Dockerfile.rocm_base
+  - vllm/models/deepseek_v41/amd/
+  - tests/models/test_dsv41_mono_numerics.py
+  - tests/models/test_dsv41_mono_layers.py
+  commands:
+  - pytest -v -s tests/models/test_dsv41_mono_numerics.py
+  - pytest -v -s tests/models/test_dsv41_mono_layers.py
+
 - label: ":amd: (MI355) Quantization Kernels Shard %N"
   timeout_in_minutes: 120
   parallelism: 6