[Bugfix][ModelLoader] Make enable_weights_track check quantized layers (#57108)
Signed-off-by: siliangchen-amd <SiLiang.Chen@amd.com> Co-authored-by: Cursor <cursoragent@cursor.com> Co-authored-by: Shanshan Shen <467638484@qq.com>
This commit is contained in:
co-authored by
Cursor
Shanshan Shen
parent
1dfe9fbdae
commit
02aa10539f
@@ -301,7 +301,10 @@ class MoERunner(MoERunnerInterface):
|
||||
def load_weights(
|
||||
self, weights: Iterable[tuple[str, torch.Tensor]]
|
||||
) -> Iterable[str]:
|
||||
return self.routed_experts.load_weights(weights)
|
||||
# routed_experts reports names relative to itself, but callers such as
|
||||
# AutoWeightsLoader qualify what this returns with the runner's prefix.
|
||||
for name in self.routed_experts.load_weights(weights):
|
||||
yield f"routed_experts.{name}"
|
||||
|
||||
def _select_forward(self) -> Callable:
|
||||
if current_platform.is_tpu():
|
||||
|
||||
Reference in New Issue
Block a user