diff --git a/tests/integration/defs/accuracy/test_llm_api_pytorch.py b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
index a65e2c70ef3e..dcf1ff8a436e 100644
--- a/tests/integration/defs/accuracy/test_llm_api_pytorch.py
+++ b/tests/integration/defs/accuracy/test_llm_api_pytorch.py
@@ -37,6 +37,7 @@
     SADecodingConfig, SamplingParams, SchedulerConfig,
     SkipSoftmaxAttentionConfig, SAEnhancerConfig, TorchCompileConfig)
 # isort: on
+from tensorrt_llm.math_utils import pad_up
 from tensorrt_llm.quantization import QuantAlgo
 
 from ..conftest import (check_device_contain, get_device_count,
@@ -3390,6 +3391,7 @@ def test_fp8_blockscale(self, tp_size, pp_size, ep_size, mtp_nextn, fp8kv,
                             attention_dp, cuda_graph, overlap_scheduler,
                             max_batch_size, moe_backend, disable_skip_indexer,
                             enable_heuristic_topk, use_cute_dsl_topk):
+        extra_llm_args = {}
         if get_sm_version() == 100 or get_sm_version() == 103:
             moe_backend = "DEEPGEMM" if moe_backend == "_DEFAULT" else moe_backend
             moe_config = MoeConfig(backend=moe_backend, max_num_tokens=16384)
@@ -3403,6 +3405,15 @@ def test_fp8_blockscale(self, tp_size, pp_size, ep_size, mtp_nextn, fp8kv,
             moe_config = MoeConfig()
             kv_cache_config = KvCacheConfig(free_gpu_memory_fraction=0.7)
 
+            # Cap max_seq_len based on the evaluation task (NVBug 6476233).
+            MAX_SEQ_LEN_GRANULARITY = 8 * 1024  # Padding boundary for max_seq_len
+
+            task_classes = (GPQADiamond, ) if fp8kv else (MMLU, GSM8K)
+            max_task_seq_len = max(task.MAX_INPUT_LEN + task.MAX_OUTPUT_LEN
+                                   for task in task_classes)
+            extra_llm_args["max_seq_len"] = pad_up(max_task_seq_len,
+                                                   MAX_SEQ_LEN_GRANULARITY)
+
         pytorch_config = dict(
             disable_overlap_scheduler=not overlap_scheduler,
             cuda_graph_config=CudaGraphConfig() if cuda_graph else None,
@@ -3442,7 +3453,8 @@ def test_fp8_blockscale(self, tp_size, pp_size, ep_size, mtp_nextn, fp8kv,
                  **pytorch_config,
                  enable_attention_dp=attention_dp,
                  speculative_config=mtp_config,
-                 sparse_attention_config=dsa_config) as llm:
+                 sparse_attention_config=dsa_config,
+                 **extra_llm_args) as llm:
 
             # GPQA Diamond takes too long to run, we enable it only for fp8kv.
             if fp8kv:
diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index 398504421c9d..da5a33e04ea0 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -163,8 +163,6 @@ full:DGX_B200/accuracy/test_llm_api_pytorch.py::TestDeepSeekV4Pro::test_gsm8k_fu
 full:DGX_B200/disaggregated/test_disaggregated.py::test_disaggregated_gpt_oss_120b_harmony[gpt_oss/gpt-oss-120b] SKIP (https://nvbugs/6594241)
 full:DGX_B200/perf/test_perf_sanity.py::test_e2e[aggr_upload-gemma4_26b_a4b_nvfp4_blackwell-gemma4_26b_a4b_nvfp4_tp1_1k1k] SKIP (https://nvbugs/6571410)
 full:DGX_B200/perf/test_perf_sanity.py::test_e2e[aggr_upload-host_perf_llama8b_spec_decode-llama8b_spec_bs1_128_128] SKIP (https://nvbugs/6571408)
-full:DGX_H200/accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[disable_skip_indexer] SKIP (https://nvbugs/6476233)
-full:DGX_H200/accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[latency_default] SKIP (https://nvbugs/6476233)
 full:GB200/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[ctx_block_reuse_only] SKIP (https://nvbugs/6525893)
 full:GB200/accuracy/test_dwdp_disaggregated_serving.py::TestDwdpDeepSeekV3Lite::test_dwdp_accuracy SKIP (https://nvbugs/6276923)
 full:GB200/accuracy/test_dwdp_disaggregated_serving.py::TestDwdpDeepSeekV3Lite::test_dwdp_accuracy_contention_opt SKIP (https://nvbugs/6276923)