FlexGen
FlexGen copied to clipboard
is cpu peak_mem monitoring work?
Thank you for the amazing project!
I was on checking opt-30B model with the provided code in readme.
python3 -m flexgen.flex_opt --model facebook/opt-30b --percent 0 100 100 0 100 0
and the result is

as I watched the progress, peak memory was 95/126GB, So I wonder is this right or, bug?
any keyword would help me, thanks!
this is not working as you expected. it is calculated by tensor size :-)
thanks for your help!