Heyang Qin c37fe9cbfb Fix exception handling in get_all_ranks_from_group() function (#4862) ... In the latest Pytorch nightly, the exception thrown from `torch.distributed.distributed_c10d.get_global_rank()` is changed from `RuntimeError` to `ValueError` so we need to update our try-catch in `deepspeed.comm` Tested with torch version 2.3.0.dev20231221+cu121 Fixes: https://github.com/microsoft/DeepSpeed/issues/4853		2023-12-22 11:48:48 -08:00
..
__init__.py	Fix for dist not being initialized when constructing main config (#3324)	2023-04-20 16:55:12 -07:00
backend.py	Correct world_size/backend for mpi (#3694)	2023-06-06 23:36:25 +00:00
ccl.py	fix error type in ccl.py (#4521)	2023-10-18 17:04:57 +00:00
comm.py	Fix exception handling in get_all_ranks_from_group() function (#4862)	2023-12-22 11:48:48 -08:00
config.py	Introduce pydantic_v1 compatibility module for pydantic>=2.0.0 support (#4407)	2023-10-09 11:59:30 -07:00
constants.py	Make Ascend NPU available (#3831)	2023-07-22 12:52:27 +00:00
reduce_op.py	[CPU] Support Intel CPU inference (#3041)	2023-05-16 11:59:22 -04:00
torch.py	CI fix for torch 2.1 release (#4452)	2023-10-05 15:31:24 -07:00
utils.py	[profiling][mics]Fix some issues for log_summary(). (#3899)	2023-07-07 19:25:15 +00:00