mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-15 07:19:53 +00:00
4f8d19ff17
* sycl: fix im2col overflow and sync with cuda Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: fix convert overflow Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: fix convert and dequantize Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: fix ib in dmmv Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl:refine convert Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * sycl: move downsample global_range into common Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * test: add im2col and convert test cases Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * test: make new cases only in sycl Signed-off-by: zhentaoyu <zhentao.yu@intel.com> * test: comment new test_cases for only local testing Signed-off-by: zhentaoyu <zhentao.yu@intel.com> --------- Signed-off-by: zhentaoyu <zhentao.yu@intel.com>
28 lines
782 B
C++
28 lines
782 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_CONVERT_HPP
|
|
#define GGML_SYCL_CONVERT_HPP
|
|
|
|
#include "common.hpp"
|
|
|
|
template <typename T>
|
|
using to_t_sycl_t = void (*)(const void *__restrict__ x, T *__restrict__ y,
|
|
int64_t k, dpct::queue_ptr stream);
|
|
typedef to_t_sycl_t<float> to_fp32_sycl_t;
|
|
typedef to_t_sycl_t<sycl::half> to_fp16_sycl_t;
|
|
|
|
to_fp16_sycl_t ggml_get_to_fp16_sycl(ggml_type type);
|
|
to_fp32_sycl_t ggml_get_to_fp32_sycl(ggml_type type);
|
|
|
|
#endif // GGML_SYCL_CONVERT_HPP
|