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

6
benchmarks/kernels/benchmark_reshape_and_cache.py
View File

@@ -84,16 +84,16 @@ def run_benchmark(
g = torch.cuda.CUDAGraph()
with torch.cuda.graph(g):
function_under_test()
torch.cuda.synchronize()
torch.accelerator.synchronize()
function_under_test = lambda: g.replay()
def run_cuda_benchmark(n_iters: int) -> float:
nonlocal key, value, key_cache, value_cache, slot_mapping
torch.cuda.synchronize()
torch.accelerator.synchronize()
start = time.perf_counter()
for _ in range(n_iters):
function_under_test()
torch.cuda.synchronize()
torch.accelerator.synchronize()
end = time.perf_counter()
return (end - start) / n_iters