Replace torch.cuda.Event with torch.Event for better hardware compatibility (#26985)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
2025-11-19 03:34:36 +08:00
parent c3e2978620
commit 2a2d5d2780
15 changed files with 41 additions and 48 deletions
--- a/benchmarks/kernels/benchmark_silu_mul_fp8_quant.py
+++ b/benchmarks/kernels/benchmark_silu_mul_fp8_quant.py
@@ -253,8 +253,8 @@ def benchmark(
        )
    torch.cuda.synchronize()

-    start_event = torch.cuda.Event(enable_timing=True)
-    end_event = torch.cuda.Event(enable_timing=True)
+    start_event = torch.Event(enable_timing=True)
+    end_event = torch.Event(enable_timing=True)

    # Benchmark
    latencies: list[float] = []