COMMITS
/ torchao/float8/float8_tensor.py December 4, 2024
L
[float8] Allow specifying arbitrary dtype for each tensor (#1378)
Luca Wehrstedt committed
November 22, 2024
V
fix bug with float8 training + FSDP2 + TP (#1327)
Vasiliy Kuznetsov committed
October 12, 2024
M
add "_gemm_input_role" to dunder slots (#984)
Masaki Kozuki committed
October 7, 2024
V
add axiswise granularity to Float8Tensor (#919)
Vasiliy Kuznetsov committed
October 1, 2024
W
[float8] improve eager numerics for dynamic scales and gets on par with torch.compile (#904)
Wei (Will) Feng committed
J
add ruff lint rule to remove unused imports via ruff (#969)
Jiayu Liu committed
September 4, 2024
D
[Float8] Make Inference and Training code independent (#808)
Driss Guessous committed
July 30, 2024
V
move float8_experimental to torchao/float8
Vasiliy Kuznetsov committed