mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-09-10 11:54:52 +00:00
Update server/text_generation_server/models/custom_modeling/flash_rw_modeling.py
Co-authored-by: OlivierDehaene <olivier@huggingface.co>
This commit is contained in:
parent
b8bfb2a91e
commit
5c82dcd2bf
@ -101,11 +101,6 @@ class FlashRWAttention(torch.nn.Module):
|
|||||||
def __init__(
|
def __init__(
|
||||||
self,
|
self,
|
||||||
config, prefix, weights,
|
config, prefix, weights,
|
||||||
# num_heads,
|
|
||||||
# num_heads_kv,
|
|
||||||
# hidden_size,
|
|
||||||
# bias,
|
|
||||||
# process_group=None,
|
|
||||||
reduce=True,
|
reduce=True,
|
||||||
):
|
):
|
||||||
super().__init__()
|
super().__init__()
|
||||||
|
Loading…
Reference in New Issue
Block a user