InternLM/internlm/moe
Wenwen Qu 95263fa1d0 merge operands in topk gating 2023-12-01 15:04:49 +08:00
..
experts.py feat(moe): add moe module (#182) 2023-09-27 15:54:53 +08:00
sharded_moe.py merge operands in topk gating 2023-12-01 15:04:49 +08:00