[Kernel/Quant] Remove the original marlin format and qqq (#23204)

Signed-off-by: mgoin <mgoin64@gmail.com>
This commit is contained in:
Michael Goin
2025-08-20 15:13:36 -04:00
committed by GitHub
parent ebe56a0064
commit 0cdbf5e61c
26 changed files with 92 additions and 3698 deletions
-3
View File
@@ -48,9 +48,6 @@ def _get_lora_device(base_layer: nn.Module) -> torch.device:
# GPTQ/AWQ
elif hasattr(base_layer, "qweight"):
return base_layer.qweight.device
# marlin
elif hasattr(base_layer, "B"):
return base_layer.B.device
# HQQ marlin
elif hasattr(base_layer, "W_q"):
return base_layer.W_q.device