[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com> Signed-off-by: Kunshang Ji <jikunshang95@gmail.com> Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
co-authored by
Harry Mellor
parent
5dc3538736
commit
16d2ad1d38
@@ -102,7 +102,7 @@ def reset_memory_stats():
|
||||
"""Reset peak memory statistics."""
|
||||
reset_buffer_cache()
|
||||
torch.cuda.reset_peak_memory_stats()
|
||||
torch.cuda.empty_cache()
|
||||
torch.accelerator.empty_cache()
|
||||
gc.collect()
|
||||
|
||||
|
||||
|
||||
@@ -54,7 +54,7 @@ def clear_triton_cache():
|
||||
|
||||
# Clear CUDA memory cache
|
||||
if torch.cuda.is_available():
|
||||
torch.cuda.empty_cache()
|
||||
torch.accelerator.empty_cache()
|
||||
|
||||
# Try to clear Triton's runtime cache
|
||||
try:
|
||||
|
||||
@@ -104,7 +104,7 @@ def run_benchmark(
|
||||
|
||||
# free tensors to mitigate OOM when sweeping
|
||||
del key, value, key_cache, value_cache, slot_mapping
|
||||
torch.cuda.empty_cache()
|
||||
torch.accelerator.empty_cache()
|
||||
|
||||
return lat
|
||||
|
||||
|
||||
@@ -129,7 +129,7 @@ def run_benchmark(
|
||||
|
||||
# free tensors to mitigate OOM when sweeping
|
||||
del key, value, key_cache, value_cache, slot_mapping
|
||||
torch.cuda.empty_cache()
|
||||
torch.accelerator.empty_cache()
|
||||
|
||||
return lat
|
||||
|
||||
|
||||
Reference in New Issue
Block a user