Morph MORPH
SIGN IN SIGN UP
dhruvhead / ao UNCLAIMED
0 0 1 Python

COMMITS

/ torchao/float8/README.md
docs
August 15, 2025
V
make e2e training benchmark support mx (#2776)
Vasiliy Kuznetsov committed
49cb18a
V
Update float8 README.md (#2774)
Vasiliy Kuznetsov committed
927cbfb
August 13, 2025
A
Drop support for PyTorch 2.5 and before (#2720)
andrewor14 committed
3bad6a2
August 11, 2025
V
torchao.float8: update with AMD MI300X benchmark results (#2736)
Vasiliy Kuznetsov committed
853f87d
July 30, 2025
V
update float8 readme with more recent performance numbers (#2580)
Vasiliy Kuznetsov committed
4b119ed
July 24, 2025
V
simplify Float8Linear (#2594)
Vasiliy Kuznetsov committed
c6de9b4
June 26, 2025
V
float8 readme: add key features section (#2448)
Vasiliy Kuznetsov committed
de57071
V
float8 readme: remove duplication (#2447)
Vasiliy Kuznetsov committed
353dd44
June 6, 2025
D
[BE/docs] Add fp8 rowwise perf table to float8 training readme (#2312)
Daniel Vega-Myhre committed
fdddb2c
June 4, 2025
V
update float8 training readme to include time measurement (#2291)
Vasiliy Kuznetsov committed
152a8e3
May 13, 2025
D
[float] document e2e training -> inference flow (#2190)
Daniel Vega-Myhre committed
a0a0969
April 1, 2025
V
refresh torchao.float8 README (#1986)
Vasiliy Kuznetsov committed
838e054
March 18, 2025
M
Add MI300X specs to roofline benchmark (#1913)
Matthias Reso committed
2db0292
March 13, 2025
D
[float8] Fix link markdown in readme (#1881)
Daniel Vega-Myhre committed
81f0bf2
March 12, 2025
D
[float8] add perf benchmarks for float8 training with rowwise + tensorwise scaling (#1793)
Daniel Vega-Myhre committed
8c81863
February 22, 2025
V
delete delayed scaling from torchao.float8 (#1753)
Vasiliy Kuznetsov committed
d370196
February 19, 2025
V
float8 training: add README.md entry for rowwise scaling (#1733)
Vasiliy Kuznetsov committed
ed16fe7
February 7, 2025
V
add a deprecation warning for float8 delayed and static scaling (#1681)
Vasiliy Kuznetsov committed
e7aa4ca
January 16, 2025
Y
Add a register_replacement to fix float8 delayed scaling kernel fusion issues in torchao/float8
y-sq committed
74a15f1
November 25, 2024
V
float8 training: move module attribute setting to sync function (#1341)
Vasiliy Kuznetsov committed
b65e513
October 29, 2024
V
clarify torchao.float8 PyTorch version support (#1191)
Vasiliy Kuznetsov committed
baa78f2
October 2, 2024
Y
Use checkpoint to enforece the recomputation of fp8 weight
y-sq committed
e919558
September 16, 2024
V
Update README.md for float8 unification (#895)
Vasiliy Kuznetsov committed
da13bf2
September 5, 2024
V
make float8 README.md examples standalone (#809)
Vasiliy Kuznetsov committed
1c488e8
September 2, 2024
V
Add performance section to float8 README.md (#794)
Vasiliy Kuznetsov committed
e2dad4a
August 28, 2024
V
float8 training: add static scaling (#760)
Vasiliy Kuznetsov committed
983f565
July 30, 2024
V
Update README.md for float8 to new feature tracker (#557)
Vasiliy Kuznetsov committed
56ac4b0
V
move float8_experimental to torchao/float8
Vasiliy Kuznetsov committed
e1aee63