mirror of
https://github.com/ROCm/ROCm.git
synced 2026-02-21 03:00:39 -05:00
* add two fp8 data types `tl.float8e4b8` and `tl.float8e5b16` to triton. * add SW type conversion between `tl.float8e4b8/tl.float8e5b16` and `fp16` * change flashattention to support fp8 in q/k.