char-fork/llama.cpp

git clone https://git.t4t.associates/char-fork/llama.cpp

Titaniumtownsycl: add a batched L2_NORM kernel (#28222)dbeb37548

char/aliceai-t5-moe
brancheschar/aliceai-t5-moeall refs →
1.2 KiB35 linesraw
1//
2// MIT license
3// Copyright (C) 2024 Intel Corporation
4// SPDX-License-Identifier: MIT
5//
6
7//
8// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
9// See https://llvm.org/LICENSE.txt for license information.
10// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
11//
12
13#ifndef GGML_SYCL_NORM_HPP
14#define GGML_SYCL_NORM_HPP
15
16#include "common.hpp"
17
18void ggml_sycl_op_norm(ggml_backend_sycl_context& ctx, ggml_tensor* dst);
19
20void ggml_sycl_op_rms_norm(ggml_backend_sycl_context& ctx, ggml_tensor* dst);
21
22void ggml_sycl_op_rms_norm_fused(ggml_backend_sycl_context& ctx, ggml_tensor* dst, ggml_tensor* mul);
23
24void ggml_sycl_op_rms_norm_fused_add(ggml_backend_sycl_context& ctx, ggml_tensor* dst, ggml_tensor* mul_tensor, ggml_tensor* add_tensor);
25
26void ggml_sycl_op_rms_norm_back(ggml_backend_sycl_context& ctx, ggml_tensor* dst);
27
28void ggml_sycl_op_group_norm(ggml_backend_sycl_context& ctx, ggml_tensor* dst);
29
30void ggml_sycl_op_l2_norm(ggml_backend_sycl_context& ctx, ggml_tensor* dst);
31
32#define GGML_SYCL_L2_BATCH_MAX 8
33void ggml_sycl_l2_norm_batch(ggml_backend_sycl_context & ctx, ggml_tensor ** nodes, int count);
34
35#endif // GGML_SYCL_NORM_HPP