llama.cpp/scripts/snapdragon/adb/run-cli.sh
Xuan-Son Nguyen 6c2131773c
cli: new CLI experience (#17824)
* wip

* wip

* fix logging, add display info

* handle commands

* add args

* wip

* move old cli to llama-completion

* rm deprecation notice

* move server to a shared library

* move ci to llama-completion

* add loading animation

* add --show-timings arg

* add /read command, improve LOG_ERR

* add args for speculative decoding, enable show timings by default

* add arg --image and --audio

* fix windows build

* support reasoning_content

* fix llama2c workflow

* color default is auto

* fix merge conflicts

* properly fix color problem

Co-authored-by: bandoti <bandoti@users.noreply.github.com>

* better loading spinner

* make sure to clean color on force-exit

* also clear input files on "/clear"

* simplify common_log_flush

* add warning in mtmd-cli

* implement console writter

* fix data race

* add attribute

* fix llama-completion and mtmd-cli

* add some notes about console::log

* fix compilation

---------

Co-authored-by: bandoti <bandoti@users.noreply.github.com>
2025-12-10 15:28:59 +01:00

54 lines
1.3 KiB
Bash
Executable File

#!/bin/sh
#
# Basedir on device
basedir=/data/local/tmp/llama.cpp
cli_opts=
branch=.
[ "$B" != "" ] && branch=$B
adbserial=
[ "$S" != "" ] && adbserial="-s $S"
model="Llama-3.2-3B-Instruct-Q4_0.gguf"
[ "$M" != "" ] && model="$M"
device="HTP0"
[ "$D" != "" ] && device="$D"
verbose=
[ "$V" != "" ] && verbose="GGML_HEXAGON_VERBOSE=$V"
experimental=
[ "$E" != "" ] && experimental="GGML_HEXAGON_EXPERIMENTAL=$E"
sched=
[ "$SCHED" != "" ] && sched="GGML_SCHED_DEBUG=2" cli_opts="$cli_opts -v"
profile=
[ "$PROF" != "" ] && profile="GGML_HEXAGON_PROFILE=$PROF GGML_HEXAGON_OPSYNC=1"
opmask=
[ "$OPMASK" != "" ] && opmask="GGML_HEXAGON_OPMASK=$OPMASK"
nhvx=
[ "$NHVX" != "" ] && nhvx="GGML_HEXAGON_NHVX=$NHVX"
ndev=
[ "$NDEV" != "" ] && ndev="GGML_HEXAGON_NDEV=$NDEV"
set -x
adb $adbserial shell " \
cd $basedir; ulimit -c unlimited; \
LD_LIBRARY_PATH=$basedir/$branch/lib \
ADSP_LIBRARY_PATH=$basedir/$branch/lib \
$verbose $experimental $sched $opmask $profile $nhvx $ndev \
./$branch/bin/llama-completion --no-mmap -m $basedir/../gguf/$model \
--poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 \
--ctx-size 8192 --batch-size 128 -ctk q8_0 -ctv q8_0 -fa on \
-ngl 99 --device $device $cli_opts $@ \
"