char-fork/llama.cpp

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

Georgi Gerganovllama : reorganize source code + improve CMake (#8006)f3f65429c

char/aliceai-t5-moe
brancheschar/aliceai-t5-moeall refs →
819 B33 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_MMQ_HPP
14#define GGML_SYCL_MMQ_HPP
15
16#include "common.hpp"
17
18void ggml_sycl_op_mul_mat_q(
19    ggml_backend_sycl_context & ctx,
20    const ggml_tensor* src0,
21    const ggml_tensor* src1,
22    ggml_tensor* dst,
23    const char* src0_dd_i,
24    const float* src1_ddf_i,
25    const char* src1_ddq_i,
26    float* dst_dd_i,
27    const int64_t row_low,
28    const int64_t row_high,
29    const int64_t src1_ncols,
30    const int64_t src1_padded_row_size,
31    const dpct::queue_ptr& stream);
32
33#endif // GGML_SYCL_MMQ_HPP