Support batched embeddings #5466
batched embedding: pool outputs by sequence id. updated embedding exa…
1549493e
bring back non-causal attention
f281d76f
embd : minor improvements
b650d4cb
Merge branch 'master' into HEAD
39d37045
llama : minor
f4cccb7e
ggerganov
approved these changes
on 2024-02-13
ggerganov
merged
03bf161e
into master 1 year ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub