[CUDA] Fix performance bug in DecoderMaskedMultiheadAttention for BeamSearch #17613
Main Optimized
11f6a18e
hariharans29
changed the title Fix performance bug in DecoderMaskedMultiheadAttention [CUDA] Fix performance bug in DecoderMaskedMultiheadAttention for BeamSearch 2 years ago
tianleiwu
approved these changes
on 2023-09-19
wangyems
approved these changes
on 2023-09-19
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub