add f8 gemm multiD with both row/col wise scale (#1300)

Browse Source

* add f8 gemm with multiD for both row/col wise

* change compute_type to fp8

* changed tuning parameters in the example

* add rcr example

...

This commit is contained in:

zjing14

2024-05-28 12:04:22 -05:00

committed by GitHub

parent 5055b3bdcb

commit 80db62f08d

6 changed files with 3955 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

2082

include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdl_cshuffle_v3_multi_d.hpp Normal file

File diff suppressed because it is too large Load Diff