a6a552e4ec
* replace llama-cli by llama-completion to rm the impact to test script * Update examples/sycl/run-llama2.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/run-llama2.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/run-llama3.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/run-llama3.sh Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/win-run-llama2.bat Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> * Update examples/sycl/win-run-llama3.bat Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com> --------- Co-authored-by: Neo Zhang Jianyu <jianyu.zhang@intel.com> Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
31 lines
1.3 KiB
Bash
Executable file
31 lines
1.3 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
|
|
# MIT license
|
|
# Copyright (C) 2025 Intel Corporation
|
|
# SPDX-License-Identifier: MIT
|
|
|
|
# If you want more control, DPC++ Allows selecting a specific device through the
|
|
# following environment variable
|
|
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/Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf
|
|
NGL=99 # Layers offloaded to the GPU. If the device runs out of memory, reduce this value according to the model you are using.
|
|
CONTEXT=4096
|
|
|
|
#support malloc device memory more than 4GB.
|
|
export UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
|
|
|
|
if [ $# -gt 0 ]; then
|
|
GGML_SYCL_DEVICE=$1
|
|
echo "Using $GGML_SYCL_DEVICE as the main GPU"
|
|
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT} -mg $GGML_SYCL_DEVICE -sm none
|
|
else
|
|
#use multiple GPUs with same max compute units
|
|
ZES_ENABLE_SYSMAN=1 ./build/bin/llama-completion -m ${MODEL_FILE} -no-cnv -p "${INPUT_PROMPT}" -n 400 -e -ngl ${NGL} -s 0 -c ${CONTEXT}
|
|
fi
|