diff --git a/tests/integration/defs/accuracy/test_llm_api_autodeploy.py b/tests/integration/defs/accuracy/test_llm_api_autodeploy.py
index 1a77e5d48604..fb1cd25a7922 100644
--- a/tests/integration/defs/accuracy/test_llm_api_autodeploy.py
+++ b/tests/integration/defs/accuracy/test_llm_api_autodeploy.py
@@ -412,6 +412,12 @@ def get_default_kwargs(self,
                            enable_chunked_prefill=False,
                            attn_backend="flashinfer"):
         yaml_paths, _ = _get_registry_yaml_extra(self.MODEL_NAME)
+        # Without chunked prefill, max_num_tokens=8192 makes the synthetic
+        # forward profile in resize_kv_cache underestimate runtime peaks
+        # (CUDA-graph capture + fp32 lm_head logits cast), causing OOM on
+        # 48GB cards. Lower the KV-cache fraction in that case to leave
+        # headroom for those post-resize allocations.
+        free_gpu_memory_fraction = 0.7 if enable_chunked_prefill else 0.5
         config = {
             "yaml_extra": yaml_paths,
             "skip_tokenizer_init": False,
@@ -420,7 +426,7 @@ def get_default_kwargs(self,
             # SSMs do not support cache reuse.
             "kv_cache_config": {
                 "enable_block_reuse": False,
-                "free_gpu_memory_fraction": 0.7
+                "free_gpu_memory_fraction": free_gpu_memory_fraction,
             },
             # 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 6dc4776bb633..f2425d03a1b8 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -244,8 +244,6 @@ full:H20/llmapi/test_llm_api_pytorch_moe_lora.py::test_qwen_moe_routed_expert_mu
 full:H20/test_e2e.py::test_qwen_e2e_cpprunner_large_new_tokens[DeepSeek-R1-Distill-Qwen-1.5B-DeepSeek-R1-Distill-Qwen-1.5B] SKIP (https://nvbugs/6414760)
 full:L40S/accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[triton-False-1] SKIP (https://nvbugs/6322045)
 full:L40S/accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[trtllm-False-1] SKIP (https://nvbugs/6322045)
-full:L40S/accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype[trtllm-flashinfer_ssm-False] SKIP (https://nvbugs/6327147)
-full:L40S/accuracy/test_llm_api_autodeploy.py::TestNemotronH::test_auto_dtype[trtllm-triton_ssm-False] SKIP (https://nvbugs/6327147)
 full:L40S/accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8[latency-torch_compile=True] SKIP (https://nvbugs/6276841)
 full:L40S/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[forced_chunked_prefill] SKIP (https://nvbugs/6327149)
 full:L40S/accuracy/test_llm_api_pytorch_multimodal.py::TestExaone4_5_33B::test_auto_dtype[full_budget] SKIP (https://nvbugs/6327149)