mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 04:31:25 +00:00
2cab8d39e3
* FA fwd dropout * FA bwd * epilogue reuse * CMakeLists update * [CK_TILE] support alibi (#1269) * add alibi support * fix code * update code based on comment * Support more hdim * fix fp8 bias * support seqlen_k=0 case * remove unused printf * fix format --------- Co-authored-by: rocking <ChunYu.Lai@amd.com> * now fwd/bwd can build * bwd alibi * add bwd validation stream_config * update generated filenames * update bwd kernel launch * CK_TILE_HOST_DEVICE in philox * Transpose -> transpose * format * format * format * Generate the instance for FA required * format * fix error in WarpGemm --------- Co-authored-by: danyao12 <danyao12> Co-authored-by: carlushuang <carlus.huang@amd.com> Co-authored-by: rocking <ChunYu.Lai@amd.com> Co-authored-by: Po Yen Chen <PoYen.Chen@amd.com> Co-authored-by: Jing Zhang <jizhan@amd.com>
22 lines
885 B
Bash
22 lines
885 B
Bash
#!/bin/sh
|
|
# TODO: run this script from CK root
|
|
BUILD=build
|
|
EXE=$BUILD/bin/tile_example_fmha_bwd
|
|
VALID=0
|
|
|
|
for prec in "fp16" "bf16" ; do
|
|
for perm in 0 1 ; do
|
|
for hdim in 32 64 128 ; do
|
|
|
|
nhead=$((2048 / $hdim)) # follow fav2 setup
|
|
$EXE -prec=$prec -b=32 -h=$nhead -d=$hdim -s=512 -iperm=$perm -operm=$perm -kname=1 -v=$VALID ; sleep 3
|
|
$EXE -prec=$prec -b=16 -h=$nhead -d=$hdim -s=1024 -iperm=$perm -operm=$perm -kname=1 -v=$VALID ; sleep 3
|
|
$EXE -prec=$prec -b=8 -h=$nhead -d=$hdim -s=2048 -iperm=$perm -operm=$perm -kname=1 -v=$VALID ; sleep 3
|
|
$EXE -prec=$prec -b=4 -h=$nhead -d=$hdim -s=4096 -iperm=$perm -operm=$perm -kname=1 -v=$VALID ; sleep 3
|
|
$EXE -prec=$prec -b=2 -h=$nhead -d=$hdim -s=8192 -iperm=$perm -operm=$perm -kname=1 -v=$VALID ; sleep 3
|
|
$EXE -prec=$prec -b=1 -h=$nhead -d=$hdim -s=16384 -iperm=$perm -operm=$perm -kname=1 -v=$VALID ; sleep 3
|
|
|
|
done
|
|
done
|
|
done
|