[CORE] Quantized lm-head Framework (#4442)
Co-authored-by: Robert Shaw <rshaw@neuralmagic.com> Co-authored-by: ZX <zx@lbx.dev>
This commit is contained in:
co-authored by
Robert Shaw
ZX
parent
7c008c51a9
commit
ee93f4f92a
@@ -83,7 +83,7 @@ def test_logits_processors(seed: int, device: str):
|
||||
device=device,
|
||||
pin_memory=is_pin_memory_available())
|
||||
logits_processor_output = logits_processor(
|
||||
embedding=None,
|
||||
lm_head=None,
|
||||
hidden_states=input_tensor,
|
||||
sampling_metadata=sampling_metadata)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user