Revert "Revert " Fp8 block scale quantization for fmha fwd (#3330)" (#3633)" (#3635)

This reverts commit de5a1d730d.

Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
This commit is contained in:
ltqin
2026-01-24 01:03:22 +08:00
committed by GitHub
parent 2e08a7e5ab
commit 67f0b74ec6
14 changed files with 667 additions and 84 deletions

View File

@@ -95,10 +95,11 @@ run_fp8bf16_tests() {
for perm in 0 1 ; do
for b in 1 2 ; do
for hdim in 64 128 256 ; do
for scale in 1 2; do
$EXE -prec=fp8bf16 -init=3 -b=$b -h=1 -d=$hdim -s=128 -iperm=$perm -operm=$perm -vlayout=r -qscale=1 -kname=$KNAME $COMMON_ARGS
$EXE -prec=fp8bf16 -init=3 -b=$b -h=1 -d=$hdim -s=128 -iperm=$perm -operm=$perm -vlayout=r -qscale=$scale -kname=$KNAME $COMMON_ARGS
done ; done ; done
done ; done ; done ; done
}
run_fp8fp32_tests() {