[https://nvbugs/6185173][fix] Set mamba ssm cache to fp32 for NemotronV2 (#14448)

Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com>
Signed-off-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>
Co-authored-by: Chenghao Zhang <211069071+nvchenghaoz@users.noreply.github.com>

Author: tensorrt-cicd

examples/auto_deploy/model_registry/configs/nemotron-nano-9b-v2.yaml

@@ -7,6 +7,9 @@ trust_remote_code: true
 kv_cache_config:
   enable_block_reuse: false
   free_gpu_memory_fraction: 0.7
+  # H20 shows an MMLU accuracy drop with the default BF16 recurrent SSM cache.
+  # Keep SSM state in FP32 for stable Triton SSM generation.
+  mamba_ssm_cache_dtype: float32
 
 # Keep max_batch_size as in the PyTorch test to avoid OOM
 max_batch_size: 128

tests/integration/test_lists/waives.txt

@@ -241,9 +241,6 @@ full:GH200/unittest/trt/model_api/test_model_quantization.py SKIP (https://nvbug
 full:H100/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-gpt_oss_120b_cutlass_stress] SKIP (https://nvbugs/6222480)
 full:H100/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-gpt_oss_120b_eagle_stress] SKIP (https://nvbugs/6222480)
 full:H100_PCIe/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_multi_lora_evict_and_reload_lora_gpu_cache SKIP (https://nvbugs/5682551)
-full:H20/accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_auto_dtype[False] SKIP (https://nvbugs/6185173)
-full:H20/accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_auto_dtype[True] SKIP (https://nvbugs/6185173)
-full:H20/accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_fp8[True] SKIP (https://nvbugs/6185173)
 full:H20/accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_chunked_prefill[triton-auto] SKIP (https://nvbugs/6026676)
 full:RTX/accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype SKIP (https://nvbugs/5569696)
 full:RTXPro6000D/accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-ep4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-low_precision_combine=False-torch_compile=False] SKIP (https://nvbugs/5948435)