Deprecate old FP8 online MoE quantization class (#44514)
Signed-off-by: Yan Ma <yan.ma@intel.com>
This commit is contained in:
@@ -65,7 +65,7 @@ class BaseModelLoader(ABC):
|
||||
|
||||
# Log peak GPU memory after loading weights. This is needed
|
||||
# to have test coverage on peak memory for online quantization.
|
||||
if current_platform.is_cuda_alike():
|
||||
if current_platform.is_cuda_alike() or current_platform.is_xpu():
|
||||
peak_memory = torch.accelerator.max_memory_allocated()
|
||||
logger.debug_once(
|
||||
"Peak GPU memory after loading weights: %s GiB",
|
||||
|
||||
Reference in New Issue
Block a user