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.

ver217 ae71036cd2 [utils] refactor parallel layers checkpoint and bcast model on loading checkpoint (#1548) ... * refactor parallel layer * broadcast rank0 model after load ckpt		2 years ago
..
__init__.py	[hotfix] Raise messages for indivisible batch sizes with tensor parallelism (#622)	3 years ago
_operation.py	[TP] change the check assert in split batch 2d (#772)	3 years ago
_utils.py	…
layers.py	[utils] refactor parallel layers checkpoint and bcast model on loading checkpoint (#1548)	2 years ago