huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 20:34:54 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: remove unused rotate_half

Browse Source
This commit is contained in:
David Holtz 2024-10-28 16:33:07 +00:00
parent f2a1b1b3fc
commit 831a07f990
1 changed files with 0 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
server/text_generation_server/models/custom_modeling/flash_qwen2_modeling.py
View File

@ -49,13 +49,6 @@ def _load_gqa(config, prefix: str, weights):
) )
def rotate_half(x):
"""Rotates half the hidden dims of the input."""
x1 = x[..., : x.shape[-1] // 2]
x2 = x[..., x.shape[-1] // 2 :]
return torch.cat((-x2, x1), dim=-1)
class Qwen2Attention(torch.nn.Module): class Qwen2Attention(torch.nn.Module):
def __init__( def __init__(
self, self,