Commit History

update
5ae9f66

Alan Liu commited on

parameter viewer
3732b01

Alan Liu commited on

use real number in model to calculate ops and para
dd4f101

Alan Liu commited on

check compute_module_sizes
d1c8a18

Alan Liu commited on

add unit
3849813

Alan Liu commited on

add client throughput
c93009d

Alan Liu commited on

add generation arithmetic intensity
ed50ee5

Alan Liu commited on

add arithmetic intensity
6aa1c8b

Alan Liu commited on

add prefill memory
5f0df3a

Alan Liu commited on

fix bug
989cd20

Alan Liu commited on

inference speed
3698d0a

Alan Liu commited on