PR #214 feat(server): reduce memory requirement

feat(server): reduce memory requirement #214

OlivierDehaene merged 4 commits into huggingface:main from njhill:tgi/mem_reduction

njhill changed the title ~~feat(server): reduce GPU memory requirement~~ feat(server): reduce memory requirement 3 years ago

feat(server): reduce memory requirement

12326eff

update unit tests

0b1d0010

njhill force pushed from e97abd2e to 0b1d0010 3 years ago

trim to new max input length in filter()

ab20142c

equivalent changes for seq2seq_lm

8e34beed

OlivierDehaene approved these changes on 2023-04-24

OlivierDehaene merged 4a7dd408 into main 3 years ago

njhill deleted the tgi/mem_reduction branch 3 years ago

Reviewers

OlivierDehaene

Assignees

No one assigned

Labels

None yet

Milestone

No milestone