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

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

Browse Source 
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:
Kunshang Ji
2026-03-04 17:49:47 +08:00
committed by GitHub
parent 5dc3538736
commit 16d2ad1d38
35 changed files with 110 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/model_executor/model_loader/tensorizer_loader/test_tensorizer.py
View File

@@ -178,7 +178,7 @@ def test_load_without_tensorizer_load_format(vllm_runner, capfd, model_ref):
finally:
del model
gc.collect()
torch.cuda.empty_cache()
torch.accelerator.empty_cache()
def test_raise_value_error_on_invalid_load_format(vllm_runner, capfd, model_ref):
@@ -200,7 +200,7 @@ def test_raise_value_error_on_invalid_load_format(vllm_runner, capfd, model_ref)
finally:
del model
gc.collect()
torch.cuda.empty_cache()
torch.accelerator.empty_cache()
@pytest.mark.skipif(torch.cuda.device_count() < 2, reason="Requires 2 GPUs")
@@ -283,7 +283,7 @@ def test_vllm_tensorized_model_has_same_outputs(
model_ref, vllm_runner, tmp_path, model_path
):
gc.collect()
torch.cuda.empty_cache()
torch.accelerator.empty_cache()
config = TensorizerConfig(tensorizer_uri=str(model_path))
args = EngineArgs(model=model_ref)