biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

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

Browse Source 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Kunshang Ji
2026-03-05 18:36:39 +08:00
committed by GitHub
parent 0bfa229bf1
commit 66a2209645
59 changed files with 158 additions and 161 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
benchmarks/kernels/benchmark_quant.py
View File

@@ -29,7 +29,7 @@ def main(
scale = torch.randn(1, 1, dtype=torch.float32) if static_scale else None
def run_cuda_benchmark(num_iters: int, profile: bool = False) -> float:
torch.cuda.synchronize()
torch.accelerator.synchronize()
if profile:
torch.cuda.cudart().cudaProfilerStart()
start_time = time.perf_counter()
@@ -39,7 +39,7 @@ def main(
ops.scaled_int8_quant(x, scale)
else:
ops.scaled_fp8_quant(x, scale)
torch.cuda.synchronize()
torch.accelerator.synchronize()
end_time = time.perf_counter()
if profile: