[Refactor] Cuda Graph Runner/Backend Refactor (#23906)

Co-authored-by: BBuf <1182563586@qq.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>

test/registered/ascend/basic_function/optimization_debug/test_npu_piecewise_graph_prefill.py

@@ -29,8 +29,8 @@ class TestPiecewiseGraphPrefillCorrectness(GSM8KAscendMixin, CustomTestCase):
         "ascend",
         "--cuda-graph-bs",
         128,
-        "--enforce-piecewise-cuda-graph",
-        "--piecewise-cuda-graph-tokens",
+        "--cuda-graph-backend-prefill=tc_piecewise",
+        "--cuda-graph-bs-prefill",
         *TOKENS_TO_CAPTURE,
     ]
     accuracy = 0.84
@@ -45,8 +45,8 @@ class TestPiecewiseGraphPrefillBenchmark(CustomTestCase):
         0.8,
         "--attention-backend",
         "ascend",
-        "--enforce-piecewise-cuda-graph",
-        "--piecewise-cuda-graph-tokens",
+        "--cuda-graph-backend-prefill=tc_piecewise",
+        "--cuda-graph-bs-prefill",
     ] + TOKENS_TO_CAPTURE
 
     latency = 0.045