Inference support for encoder-decoder architecture #2451
RezaYazdaniAminabadi
wants to merge
6 commits into
master
from
inference/support-encoder-decoder
fixing the softmax masking when using triangular masking
f7ef4b5e
Merge branch 'master' of github.com:microsoft/DeepSpeed
dfb603fe
adding support for encoder-decoder kernel-injection with tensor paral…
7ac4ab74
add the decoder transformer-api
df33a000
add some minor changes
94515902
fixing som issue for encoder-decoder inference
497792ed
RezaYazdaniAminabadi
changed the title 
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub