mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-08-29 00:21:21 +02:00
Fathi Boudra
0177dcc730
Replace the deprecated --mmap, --no-mmap, --mlock, and --direct-io flags with the unified --load-mode argument across scripts, examples, and documentation. Internal warning message and env var docs updated accordingly. Signed-off-by: Fathi Boudra <fathi.boudra@linaro.org>
12 lines
481 B
Batchfile
12 lines
481 B
Batchfile
:: MIT license
|
|
:: Copyright (C) 2024 Intel Corporation
|
|
:: SPDX-License-Identifier: MIT
|
|
|
|
set INPUT2="Building a website can be done in 10 simple steps:\nStep 1:"
|
|
@call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat" intel64 --force
|
|
|
|
:: support malloc device memory more than 4GB.
|
|
set UR_L0_ENABLE_RELAXED_ALLOCATION_LIMITS=1
|
|
set LOAD_MODE="--load-mode auto"
|
|
.\build\bin\llama-completion.exe -m models\llama-2-7b.Q4_0.gguf -no-cnv -p %INPUT2% -n 400 -e -ngl 99 -s 0 %LOAD_MODE%
|