[Hardware] Replace torch.cuda.synchronize() api with torch.accelerator.synchronize (#36085)

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
2026-03-05 18:36:39 +08:00
parent 0bfa229bf1
commit 66a2209645
59 changed files with 158 additions and 161 deletions
--- a/benchmarks/kernels/benchmark_per_token_group_quant.py
+++ b/benchmarks/kernels/benchmark_per_token_group_quant.py
@@ -28,7 +28,7 @@ def _time_cuda(
    # warmup
    for _ in range(warmup_iters):
        fn()
-    torch.cuda.synchronize()
+    torch.accelerator.synchronize()

    start = torch.Event(enable_timing=True)
    end = torch.Event(enable_timing=True)
@@ -37,7 +37,7 @@ def _time_cuda(
    for _ in range(bench_iters):
        fn()
    end.record()
-    torch.cuda.synchronize()
+    torch.accelerator.synchronize()

    return start.elapsed_time(end) / bench_iters  # ms/iter