tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 14:18:50 -04:00
Code Issues Packages Projects Releases 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
14 changed files with 803 additions and 266 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/sycl/run-llama2.sh
View File

@@ -3,7 +3,7 @@
# MIT license
# Copyright (C) 2024 Intel Corporation
# SPDX-License-Identifier: MIT
export ONEAPI_DEVICE_SELECTOR="level_zero:0"
source /opt/intel/oneapi/setvars.sh
#export GGML_SYCL_DEBUG=1
@@ -13,7 +13,7 @@ source /opt/intel/oneapi/setvars.sh
INPUT_PROMPT="Building a website can be done in 10 simple steps:\nStep 1:"
MODEL_FILE=models/llama-2-7b.Q4_0.gguf
NGL=33
CONEXT=8192
CONEXT=4096
if [ $# -gt 0 ]; then
GGML_SYCL_DEVICE=$1