You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

1SAA 219df6e685 Optimized MoE layer and fixed some bugs; ... Decreased moe tests; Added FFNExperts and ViTMoE model		3 years ago
..
cuda_native	Optimized MoE layer and fixed some bugs;	3 years ago
jit	adapted for sequence parallel (#163)	3 years ago
__init__.py	refactor kernel (#142)	3 years ago