[ROCm][CI] Add missing quantization methods and fix online quant test failures (#39801)

Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2026-04-27 15:08:57 -05:00
committed by GitHub
parent c8bbe05189
commit 5e2c37facd
9 changed files with 50 additions and 23 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():
if current_platform.is_cuda_alike():
peak_memory = torch.accelerator.max_memory_allocated()
logger.debug_once(
"Peak GPU memory after loading weights: %s GiB",