Cognitive Computations's repositories
dolphin-system-messages
Dolphin System Messages
extract-expert
Extract a single expert from a Mixture Of Experts model using slerp interpolation.
SequoiaMPS
scalable and robust tree-based speculative decoding algorithm
onju-voice
A hackable AI home assistant platform
DeepSpeed
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
Language:PythonApache-2.0000
Language:Python000