mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-11-02 09:12:03 +00:00
08d5986290
* 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>
28 lines
941 B
Bash
Executable File
28 lines
941 B
Bash
Executable File
#!/bin/bash
|
|
|
|
# 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
|
|
|
|
#ZES_ENABLE_SYSMAN=1, Support to get free memory of GPU by sycl::aspect::ext_intel_free_memory. Recommended to use when --split-mode = layer.
|
|
|
|
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=4096
|
|
|
|
if [ $# -gt 0 ]; then
|
|
GGML_SYCL_DEVICE=$1
|
|
echo "use $GGML_SYCL_DEVICE as main GPU"
|
|
#use signle GPU only
|
|
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT} -mg $GGML_SYCL_DEVICE -sm none
|
|
|
|
else
|
|
#use multiple GPUs with same max compute units
|
|
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-cli -m ${MODEL_FILE} -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONEXT}
|
|
fi
|