diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index abf8522a9f40..5704fa50adc4 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -322,7 +322,6 @@ unittest/_torch/attention/sparse/dsa/test_req_idx_per_token.py::test_on_update_k
 unittest/_torch/attention/test_attention_backends.py::test_attention_backend[deepseekv3_mla-gen-bf16-HND-p32-v1] SKIP (https://nvbugs/6507109)
 unittest/_torch/executor/test_overlap_scheduler.py::test_overlap_scheduler_consistency[no_reuse-cpp_scheduler-TorchSampler] SKIP (https://nvbugs/6561559)
 unittest/_torch/misc/test_autotuner.py::test_cutedsl_nvfp4_heuristic_matches_full_sweep SKIP (https://nvbugs/6490028)
-unittest/_torch/modeling/test_kimi_kda_verify_parity.py::test_kda_verify_matches_sequential_decode[2-1] SKIP (https://nvbugs/6599150)
 unittest/_torch/modeling/test_modeling_qwen_moe.py::TestQwenMoe::test_qwen_moe_allclose_to_hf[backend:trtllm-use_cuda_graph:False] SKIP (https://nvbugs/6566765)
 unittest/_torch/modeling/test_modeling_qwen_moe.py::TestQwenMoe::test_qwen_moe_allclose_to_hf[backend:trtllm-use_cuda_graph:True] SKIP (https://nvbugs/6575012)
 unittest/_torch/modeling/test_modeling_qwen_moe.py::TestQwenMoe::test_qwen_moe_allclose_to_hf[backend:vanilla-use_cuda_graph:False] SKIP (https://nvbugs/6566765)
diff --git a/tests/unittest/_torch/modeling/test_kimi_kda_verify_parity.py b/tests/unittest/_torch/modeling/test_kimi_kda_verify_parity.py
index 0b20cfc34bd2..f23ba5983313 100644
--- a/tests/unittest/_torch/modeling/test_kimi_kda_verify_parity.py
+++ b/tests/unittest/_torch/modeling/test_kimi_kda_verify_parity.py
@@ -59,6 +59,10 @@ def test_kda_verify_matches_sequential_decode(batch, t_steps):
     w = lin["short_conv_kernel_size"]
 
     runtime = KimiKDARuntime(cfg, layer_idx=0).to(device)
+    # dt_bias is torch.empty at construction and only filled by
+    # load_weights(); with random weights it holds heap garbage, and a
+    # NaN/Inf bit pattern poisons both paths identically (nvbug 6599150).
+    torch.nn.init.normal_(runtime.mixer.dt_bias, std=0.1)
     slots = batch + 2  # non-trivial slot mapping
     cache = _LayerCache(slots, 3 * dim, w, h, lin["head_dim"], lin["head_dim"], t_steps, device)
     slot_indices = torch.arange(2, 2 + batch, device=device, dtype=torch.long)