Making large AI models cheaper, faster and more accessible
COMMITS
/ extensions/__init__.py April 24, 2024
April 8, 2024
Y
[Fix] resolve conflicts of merging main
Yuanheng committed
March 27, 2024
H
[shardformer] update colo attention to support custom mask (#5510)
Hongxin Liu committed
February 28, 2024
Y
[Inference]Add CUDA KVCache Kernel (#5406)
yuehuayingxueluo committed
January 25, 2024
F
[feat] refactored extension module (#5298)
Frank Lee committed