diff --git a/tensorrt_llm/_torch/pyexecutor/py_executor.py b/tensorrt_llm/_torch/pyexecutor/py_executor.py
index f69041fa7ab8..fb74cca97eea 100644
--- a/tensorrt_llm/_torch/pyexecutor/py_executor.py
+++ b/tensorrt_llm/_torch/pyexecutor/py_executor.py
@@ -3002,10 +3002,14 @@ def _ring_broadcast_sample_state(
         if not self.dist.is_last_pp_rank:
             # Receive tokens from previous pp rank (w.r.t model forward direction)
             with nvtx_range("recv_sample_state"):
-                sample_state.host, py_result_diffs = self.dist.recv_object(
+                sample_state.host, py_result_diffs, use_host_stop_criteria = self.dist.recv_object(
                     src=self.dist.prev_pp_rank,
                     tag=tag,
                 )
+            # Propagate the last-rank fast-path decision so update_requests on
+            # this rank matches how state.host was populated on the last rank.
+            if hasattr(sample_state, "use_host_stop_criteria"):
+                sample_state.use_host_stop_criteria = use_host_stop_criteria
 
             for request, py_result_diff in zip(requests, py_result_diffs):
                 request.py_result.apply_diff(py_result_diff)
@@ -3023,7 +3027,8 @@ def _ring_broadcast_sample_state(
             self.wait_on_pp_send_handles(self.send_handles, microbatch_id)
             with nvtx_range("send_sample_state"):
                 self.send_handles[microbatch_id] = self.dist.isend_object(
-                    (sample_state.host, py_result_diffs),
+                    (sample_state.host, py_result_diffs,
+                     getattr(sample_state, "use_host_stop_criteria", False)),
                     dest=self.dist.next_pp_rank,
                     tag=tag,
                 )
diff --git a/tests/integration/test_lists/waives.txt b/tests/integration/test_lists/waives.txt
index e1d3b85239b6..dd6e9d290ae3 100644
--- a/tests/integration/test_lists/waives.txt
+++ b/tests/integration/test_lists/waives.txt
@@ -66,7 +66,6 @@ accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backe
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-pp4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-low_precision_combine=False-torch_compile=False] SKIP (https://nvbugs/5945081)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-pp4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-low_precision_combine=False-torch_compile=True] SKIP (https://nvbugs/6384625)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-pp4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-low_precision_combine=False-torch_compile=False] SKIP (https://nvbugs/6427411)
-accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-pp4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-low_precision_combine=False-torch_compile=True] SKIP (https://nvbugs/6428063)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-tp2pp2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-low_precision_combine=False-torch_compile=False] SKIP (https://nvbugs/6384625)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-tp2pp2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-low_precision_combine=False-torch_compile=True] SKIP (https://nvbugs/6384625)
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-tp4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-low_precision_combine=False-torch_compile=True] SKIP (https://nvbugs/6272673)