Files
tinygrad/test/unit
chenyu c07daf40e7 move attention upcast (#7830)
still upcast before softmax, but faster because intermediate buffer can be stored in half (as long as qk is within half range).
2024-11-22 17:10:51 -05:00
..
2023-12-05 16:17:57 -08:00
2024-10-25 17:05:09 +07:00
2024-11-03 11:26:10 +08:00