Merge branch 'develop' into codegen-enable-hiprtc

example/ck_tile/09_topk_softmax/topk_softmax_api.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+
+#pragma once
+#include "ck_tile/core.hpp"
+#include "ck_tile/host.hpp"
+#include "ck_tile/ops/topk_softmax.hpp"
+#include <string>
+
+struct topk_softmax_trait
+{
+    std::string input_type;
+    std::string weight_type; // currently always float
+    int experts;
+};
+
+struct topk_softmax_kargs : public ck_tile::TopkSoftmaxHostArgs
+{
+};
+
+float topk_softmax(topk_softmax_trait t, topk_softmax_kargs a, ck_tile::stream_config s);

example/ck_tile/10_rmsnorm2d/README.md

+# Rmsnorm2D forward
+
+This folder contains example for Rmsnorm2D forward using ck_tile tile-programming implementation.
+
+## build
+```
+# in the root of ck_tile
+mkdir build && cd build
+sh ../script/cmake-ck-dev.sh  ../ <arch>  # you can replace this <arch> to gfx90a, gfx942...
+make tile_rmsnorm2d_fwd -j
+```
+This will result in an executable `build/bin/tile_rmsnorm2d_fwd`
+
+## cmdline
+```
+args:
+          -m    m dimension (default:3328)
+          -n    m dimension (default:4096)
+          -e    epsilon (default:1e-5)
+          -v    cpu validation or not (default:1)
+       -prec    precision (default:fp16)
+```