Contextual Correction of Parallel Draftsfor Speculative Decoding
DCOCO restores intra-block context in parallel speculative drafts, reaching up to 6.6x decoding speedup.
1 stories, newest first · one card per story
DCOCO restores intra-block context in parallel speculative drafts, reaching up to 6.6x decoding speedup.
Today 2.6K readers · 2.9K views · 145 reads · all time 206K views