diff --git a/example/ck_tile/01_fmha/README.md b/example/ck_tile/01_fmha/README.md
index f72d7afa02..f2d60a250f 100644
--- a/example/ck_tile/01_fmha/README.md
+++ b/example/ck_tile/01_fmha/README.md
@@ -129,4 +129,4 @@ TBD
 ## FP8 experimental support
 As described in [this blog](https://blog.hippoml.com/8bit-hippoattention-up-to-3x-faster-compared-to-flashattentionv2-8f9def90b482), we have an experimental support for fp8 fmha kernels, you can evaluate the performance by setting the arg `-prec=fp8` to the `tile_example_fmha_fwd`, on a gfx942 machine and ROCm 6.0+.
 
-Currently we only support `-vlayout=c`( `hdim*seqlen` for V matrix) and `-squant=1`(static quantization) with `hdim=128` for fp8 now. Full feature support will come later.
+Currently we  support `-vlayout=r`( `hdim*seqlen` for V matrix) and `-squant=1`(static quantization) with `hdim=128` for fp8 now. Full feature support will come later.
diff --git a/example/ck_tile/01_fmha/script/smoke_test_fwd.sh b/example/ck_tile/01_fmha/script/smoke_test_fwd.sh
index 3913a0d5c2..ca2199ad0a 100755
--- a/example/ck_tile/01_fmha/script/smoke_test_fwd.sh
+++ b/example/ck_tile/01_fmha/script/smoke_test_fwd.sh
@@ -73,7 +73,7 @@ run_fp8_tests() {
     for b in 1 2 ; do
     for hdim in 64 128 256 ; do
     
-    $EXE -prec=fp8 -init=3 -b=$b -h=1 -d=128 -s=128 -bias=$bias -iperm=$perm -operm=$perm -vlayout=c -squant=1 -kname=$KNAME $COMMON_ARGS  
+    $EXE -prec=fp8 -init=3 -b=$b -h=1 -d=128 -s=128 -bias=$bias -iperm=$perm -operm=$perm -vlayout=r -squant=1 -kname=$KNAME $COMMON_ARGS
 
     done ; done ; done ; done
 }