ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

[SYCL] Optimize mul_mat for Q4_0 on Intel GPU (#12035)

Browse source 
* opt performance by reorder for Intel GPU

* detect hw type and save opt feature, and print opt feature

* correct name

* support optimize graph once when compute graph, record the opt status in tensor->extra, make CI passed

* add env variable GGML_SYCL_DISABLE_OPT for debug

* use syclex::architecture replace the custom hw define, update the guide for GGML_SYCL_DISABLE_OPT

* add performance data

* mv getrows functions to separeted files

* fix global variables

---------

Co-authored-by: arthw <14088817+arthw@users.noreply.github.com>
This commit is contained in:
Neo Zhang Jianyu 2025-02-24 22:33:23 +08:00 • committed by GitHub
parent 651adf4b66
commit 08d5986290
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
14 changed files with 803 additions and 266 deletions
Download patch file Download diff file Expand all files Collapse all files

23
ggml/src/ggml-sycl/getrows.hpp Normal file
View file

@ -0,0 +1,23 @@
//
// 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_GETROWS_HPP
#define GGML_SYCL_GETROWS_HPP
#include "common.hpp"
void ggml_sycl_op_get_rows(ggml_backend_sycl_context & ctx, const ggml_tensor *src0,
const ggml_tensor *src1, ggml_tensor *dst,
const float *src0_d, const float *src1_d,
float *dst_d, const queue_ptr &stream);
#endif // GGML_SYCL_GETROWS_HPP