justheuristic 5af04524dd Split long sequences into chunks (#403) ... This PR is designed to avoid OOMs when processing long sequences that happen due to the huge attention logits matrices. Co-authored-by: Alexander Borzunov <borzunov.alexander@gmail.com>		2023-07-22 23:10:46 +04:00
..
check-style.yaml	Add Python 3.10 to CI (#299)	2023-03-29 04:41:07 +04:00
push-docker-image.yaml	Merge inference pools into one to increase inference speed (#225)	2023-01-19 19:38:21 +04:00
run-tests.yaml	Split long sequences into chunks (#403)	2023-07-22 23:10:46 +04:00