mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-07-16 15:47:35 +00:00
17512a94d6
* sycl : Implemented reorder Q4_0 mmvq Signed-off-by: Alberto Cabrera <alberto.cabrera@codeplay.com> * sycl : Fixed mmvq being called when reorder is disabled * sycl : Improved comments in the quants header Signed-off-by: Alberto Cabrera <alberto.cabrera@codeplay.com> * Use static_assert * safe_div -> ceil_div * Clarify qi comment * change the reorder tensor from init to execute OP * dbg * Undo changes to test-backend-ops * Refactor changes on top of q4_0 reorder fix * Missing Reverts * Refactored opt_for_reorder logic to simplify code path * Explicit inlining and unroll * Renamed mul_mat_algo enum for consistency --------- Signed-off-by: Alberto Cabrera <alberto.cabrera@codeplay.com> Co-authored-by: romain.biessy <romain.biessy@codeplay.com>
38 lines
830 B
C++
38 lines
830 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_BACKEND_HPP
|
|
#define GGML_SYCL_BACKEND_HPP
|
|
|
|
#include "binbcast.hpp"
|
|
#include "common.hpp"
|
|
#include "concat.hpp"
|
|
#include "conv.hpp"
|
|
#include "convert.hpp"
|
|
#include "cpy.hpp"
|
|
#include "dequantize.hpp"
|
|
#include "dmmv.hpp"
|
|
#include "element_wise.hpp"
|
|
#include "gla.hpp"
|
|
#include "im2col.hpp"
|
|
#include "mmq.hpp"
|
|
#include "mmvq.hpp"
|
|
#include "norm.hpp"
|
|
#include "outprod.hpp"
|
|
#include "quants.hpp"
|
|
#include "rope.hpp"
|
|
#include "softmax.hpp"
|
|
#include "tsembd.hpp"
|
|
#include "wkv.hpp"
|
|
|
|
#endif // GGML_SYCL_BACKEND_HPP
|