Infini-AI-Lab

Results 2 repositories owned by Infini-AI-Lab

Sequoia

305
Stars
31
Forks
Watchers

scalable and robust tree-based speculative decoding algorithm

TriForce

209
Stars
12
Forks
Watchers

[COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding