Benjamin Trent 52de9d169b [ML] fixing potential network thread lockup on Pytorch model load (#75784) ... After the model is loaded via the search request, that searching thread MAY be a network thread. Consequently, we should not lock it up while creating the named pipes. This commit addresses by forcing named pipe creation to be done within the ML_UTILITY executor threadpool.		2021-07-28 13:42:14 -04:00
..
licenses	[ML] Remove the undocumented "delimited" format for post_data (#74188)	2021-06-17 15:30:27 +01:00
qa	[ML] Mute PyTorchModelIT in advance of input format changes (#75800)	2021-07-28 17:59:04 +01:00
src	[ML] fixing potential network thread lockup on Pytorch model load (#75784)	2021-07-28 13:42:14 -04:00
build.gradle	[ML] Integrating ML with the node shutdown API (#75188)	2021-07-22 19:24:23 +01:00