diff --git a/examples/auto_deploy/model_registry/configs/nemotron-nano-9b-v2.yaml b/examples/auto_deploy/model_registry/configs/nemotron-nano-9b-v2.yaml index c9066452d78a..ac93d4a3bc37 100644 --- a/examples/auto_deploy/model_registry/configs/nemotron-nano-9b-v2.yaml +++ b/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 diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt index d8b55a45d21b..6e101b74edda 100644 --- a/tests/integration/test_lists/waives.txt +++ b/tests/integration/test_lists/waives.txt @@ -279,9 +279,6 @@ full:GH200/examples/test_nemotron.py::test_llm_nemotron_3_8b_1gpu[bfloat16-fp8] full:GH200/examples/test_qwen2audio.py::test_llm_qwen2audio_single_gpu[qwen2_audio_7b_instruct] SKIP (arm is not supported) full:GH200/unittest/trt/model_api/test_model_quantization.py SKIP (https://nvbugs/4979955) 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)