freedak/timesfm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

minor doc changes

Browse Source
This commit is contained in:
Rajat Sen
2025-10-01 21:47:42 +00:00
parent 4f6bf5adc0
commit a58bde615d
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/timesfm/torch/transformer.py
+1 -1
View File
@@ -131,7 +131,7 @@ def _dot_product_attention(
def _torch_dot_product_attention(query, key, value, mask=None): def _torch_dot_product_attention(query, key, value, mask=None):
""" """
Performs the exact same (unscaled) attention as your original function, Performs the exact same (unscaled) attention as the above function,
but using the fast and fused F.scaled_dot_product_attention kernel. but using the fast and fused F.scaled_dot_product_attention kernel.
""" """