InternLM/internlm/moe
zhanglei edc18bcddd fix precision inconsistency 2023-09-18 20:54:52 +08:00
..
experts.py replace flashatten experts by feedforward experts 2023-09-08 18:04:57 +08:00
sharded_moe.py fix precision inconsistency 2023-09-18 20:54:52 +08:00