Skip to content

Activity

Update LICENSE

thevasudevguptapushed 1 commit to main • f1dc67c…6a12b71 • 
on Aug 28, 2024

Update LICENSE

thevasudevguptapushed 1 commit to main • a10ebd7…f1dc67c • 
on Aug 28, 2024

Update README.md

thevasudevguptapushed 1 commit to main • 5c9ff7a…a10ebd7 • 
on Aug 28, 2024

Update README.md

thevasudevguptapushed 1 commit to main • 1c6c307…5c9ff7a • 
on Aug 28, 2024

Update README.md

thevasudevguptapushed 1 commit to main • c927a68…1c6c307 • 
on Aug 28, 2024

Update README.md

thevasudevguptapushed 1 commit to main • c25ba98…c927a68 • 
on Aug 28, 2024

add correct MFU - fwd only

thevasudevguptapushed 1 commit to main • 1d94e00…c25ba98 • 
on Aug 25, 2024

Update bench.py

thevasudevguptapushed 1 commit to main • 66eacf0…1d94e00 • 
on Aug 25, 2024

Update kernels.py

thevasudevguptapushed 1 commit to main • 6b74c53…66eacf0 • 
on Aug 25, 2024

Update kernels.py

thevasudevguptapushed 1 commit to main • cc41721…6b74c53 • 
on Aug 25, 2024

Update README.md

thevasudevguptapushed 1 commit to main • 234edbd…cc41721 • 
on Aug 25, 2024

remove mfu as its likely wrong

thevasudevguptapushed 1 commit to main • 397314a…234edbd • 
on Aug 25, 2024

add mfu

thevasudevguptapushed 1 commit to main • 08b927f…397314a • 
on Aug 25, 2024

Update README.md

thevasudevguptapushed 1 commit to main • 4828b59…08b927f • 
on Aug 24, 2024

Update bench.py

thevasudevguptapushed 1 commit to main • f1bf06f…4828b59 • 
on Aug 24, 2024

Update README.md

thevasudevguptapushed 1 commit to main • 4468fd0…f1bf06f • 
on Aug 24, 2024

remove cast_dtype_for_dot as it slows down a lot; fixes for a100; add…

thevasudevguptapushed 1 commit to main • 4d40ca2…4468fd0 • 
on Aug 24, 2024

add flops, mfu, time etc

thevasudevguptapushed 1 commit to main • 41680d7…4d40ca2 • 
on Aug 24, 2024

Update README.md

thevasudevguptapushed 1 commit to main • a65370d…41680d7 • 
on Aug 23, 2024

Update README.md

thevasudevguptapushed 1 commit to main • d0c6db6…a65370d • 
on Aug 23, 2024

Update README.md

thevasudevguptapushed 1 commit to main • f7452f2…d0c6db6 • 
on Aug 23, 2024

done for today

thevasudevguptapushed 1 commit to main • 6eb36de…f7452f2 • 
on Aug 23, 2024

fp32 precision pass all tests except gpt test

thevasudevguptapushed 1 commit to main • a896149…6eb36de • 
on Aug 23, 2024

save progress

thevasudevguptapushed 1 commit to main • 776e5e7…a896149 • 
on Aug 23, 2024

this runs on gpy

thevasudevguptapushed 1 commit to main • 60f6553…776e5e7 • 
on Aug 23, 2024

lets run test on gpu

thevasudevguptapushed 1 commit to main • 5b2a1ef…60f6553 • 
on Aug 23, 2024

not perfect match but close

thevasudevguptapushed 1 commit to main • a48adc2…5b2a1ef • 
on Aug 23, 2024

fwd pass runs

thevasudevguptapushed 1 commit to main • 4de4a16…a48adc2 • 
on Aug 23, 2024

Update LICENSE

thevasudevguptapushed 1 commit to main • 53cbb0a…4de4a16 • 
on Aug 23, 2024

save progress

thevasudevguptapushed 1 commit to main • f367e81…53cbb0a • 
on Aug 23, 2024