InternLM/internlm/core
Wenwen Qu 86bcda5ca9 add default setting for expert parallel size 2023-08-24 18:52:12 +08:00
..
communication fix(ci): fix ci train error (#199) 2023-08-15 20:09:54 +08:00
context add default setting for expert parallel size 2023-08-24 18:52:12 +08:00
scheduler add support for moe checkpoint 2023-08-24 17:01:14 +08:00
__init__.py initial commit 2023-07-06 12:55:23 +08:00
engine.py initial commit 2023-07-06 12:55:23 +08:00
gradient_handler.py initial commit 2023-07-06 12:55:23 +08:00
naive_amp.py refactor(scheduler): rewrite pipeline scheduler (#138) 2023-08-03 11:48:12 +08:00
trainer.py add logger for moe_loss 2023-08-17 16:52:11 +08:00