Skip to content

Commit 576b1be

Browse files
Implementing speculative decoding for batch_size > 1; applicable if target and draft model have the same tokenizer.
1 parent 47e795b commit 576b1be

File tree

4 files changed

+449
-112
lines changed

4 files changed

+449
-112
lines changed

0 commit comments

Comments
 (0)