diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index e50b692a3dc..181f48affe8 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -379,7 +379,6 @@ accuracy/test_llm_api_pytorch.py::TestNemotronUltra::test_fp8_prequantized[tp8-c
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_chunked_prefill[cutlass-auto] SKIP (https://nvbugs/5596343)
 unittest/_torch/speculative/test_spec_gate.py::test_spec_gate_e2e SKIP (https://nvbugs/5710045)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=TRTLLM-mtp_nextn=0-ep4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5721661)
-unittest/_torch/auto_deploy/unit/singlegpu/custom_ops/test_flashinfer_attention_op.py::test_flashinfer_attention_op_context_input_pos[cuda-dtype0-4-8-seq6] SKIP (https://nvbugs/5721907)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4[moe_backend=CUTLASS-mtp_nextn=0-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] SKIP (https://nvbugs/5722629)
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_2gpus[cutlass-two_model-overlap_scheduler] SKIP (https://nvbugs/5702826)
 accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_eagle3_4gpus[cutlass-two_model-overlap_scheduler] SKIP (https://nvbugs/5702826)
diff --git a/tests/unittest/_torch/auto_deploy/unit/singlegpu/custom_ops/test_flashinfer_attention_op.py b/tests/unittest/_torch/auto_deploy/unit/singlegpu/custom_ops/test_flashinfer_attention_op.py
index e27477112fa..9ce3dcd8ecf 100644
--- a/tests/unittest/_torch/auto_deploy/unit/singlegpu/custom_ops/test_flashinfer_attention_op.py
+++ b/tests/unittest/_torch/auto_deploy/unit/singlegpu/custom_ops/test_flashinfer_attention_op.py
@@ -574,6 +574,17 @@ def test_flashinfer_attention_op_context_input_pos(seq, batch_size, n_heads, dty
         (MAX_BATCH_SIZE, MAX_SEQ_LEN, N_HEADS, D_HEAD), dtype=DTYPE, device=device
     )
 
+    # Initialize the prefilled portion of the cache with random data
+    # This simulates a chunked prefill scenario where previous chunks have already
+    # populated the cache at positions 0:PREFILL_SEQ_LEN
+    if PREFILL_SEQ_LEN > 0:
+        k_cache[0:BATCH_SIZE, 0:PREFILL_SEQ_LEN, :, :] = torch.randn(
+            BATCH_SIZE, PREFILL_SEQ_LEN, N_HEADS, D_HEAD, dtype=DTYPE, device=device
+        )
+        v_cache[0:BATCH_SIZE, 0:PREFILL_SEQ_LEN, :, :] = torch.randn(
+            BATCH_SIZE, PREFILL_SEQ_LEN, N_HEADS, D_HEAD, dtype=DTYPE, device=device
+        )
+
     # make sure planner is initialized
     workspace = torch.empty(128 * 1024 * 1024, dtype=torch.uint8, device=device)
     _GlobalFlashInferPlanner.init_workspace(workspace)