Deprecate old FP8 online MoE quantization class (#44514)

Signed-off-by: Yan Ma <yan.ma@intel.com>
This commit is contained in:
Yan Ma
2026-06-23 11:53:38 -07:00
committed by GitHub
parent 68afd78897
commit acce57d8dd
3 changed files with 19 additions and 137 deletions
@@ -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",