mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-15 07:19:53 +00:00
f3f65429c4
* scripts : update sync [no ci] * files : relocate [no ci] * ci : disable kompute build [no ci] * cmake : fixes [no ci] * server : fix mingw build ggml-ci * cmake : minor [no ci] * cmake : link math library [no ci] * cmake : build normal ggml library (not object library) [no ci] * cmake : fix kompute build ggml-ci * make,cmake : fix LLAMA_CUDA + replace GGML_CDEF_PRIVATE ggml-ci * move public backend headers to the public include directory (#8122) * move public backend headers to the public include directory * nix test * spm : fix metal header --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> * scripts : fix sync paths [no ci] * scripts : sync ggml-blas.h [no ci] --------- Co-authored-by: slaren <slarengh@gmail.com>
34 lines
819 B
C++
34 lines
819 B
C++
//
|
|
// MIT license
|
|
// Copyright (C) 2024 Intel Corporation
|
|
// SPDX-License-Identifier: MIT
|
|
//
|
|
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
|
|
#ifndef GGML_SYCL_MMQ_HPP
|
|
#define GGML_SYCL_MMQ_HPP
|
|
|
|
#include "common.hpp"
|
|
|
|
void ggml_sycl_op_mul_mat_q(
|
|
ggml_backend_sycl_context & ctx,
|
|
const ggml_tensor* src0,
|
|
const ggml_tensor* src1,
|
|
ggml_tensor* dst,
|
|
const char* src0_dd_i,
|
|
const float* src1_ddf_i,
|
|
const char* src1_ddq_i,
|
|
float* dst_dd_i,
|
|
const int64_t row_low,
|
|
const int64_t row_high,
|
|
const int64_t src1_ncols,
|
|
const int64_t src1_padded_row_size,
|
|
const dpct::queue_ptr& stream);
|
|
|
|
#endif // GGML_SYCL_MMQ_HPP
|