[Bugfix] LoRA for DeepSeek V3.2 (#35077)

Signed-off-by: Hollow Man <hollowman@opensuse.org>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
2026-04-22 19:33:50 +08:00
committed by GitHub
co-authored by mergify[bot] <37929162+mergify[bot]@users.noreply.github.com> Jee Jee Li
parent 04eac6ba24
commit a250f1bd5f
13 changed files with 614 additions and 37 deletions
+9
View File
@@ -203,7 +203,16 @@ class BaseLinearLayerWithLoRA(BaseLayerWithLoRA):
self, x: torch.Tensor, bias: torch.Tensor | None = None
) -> torch.Tensor:
output = self.base_layer.quant_method.apply(self.base_layer, x, bias)
return self._apply_lora_to_output(x, output)
def _apply_base_forward(self, x: torch.Tensor) -> torch.Tensor:
base_output = self.base_layer(x)
output = base_output[0] if isinstance(base_output, tuple) else base_output
return self._apply_lora_to_output(x, output)
def _apply_lora_to_output(
self, x: torch.Tensor, output: torch.Tensor
) -> torch.Tensor:
original_shape = output.shape if output.ndim == 3 else None
# In transformers backend, x and output have extra batch dimension like