[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
@@ -49,7 +49,7 @@ def test_gc():
|
||||
del llm
|
||||
|
||||
gc.collect()
|
||||
torch.cuda.empty_cache()
|
||||
torch.accelerator.empty_cache()
|
||||
|
||||
# The memory allocated for model and KV cache should be released.
|
||||
# The memory allocated for PyTorch and others should be less than 50MB.
|
||||
|
||||
Reference in New Issue
Block a user