mirror of
https://github.com/LostRuins/koboldcpp.git
synced 2026-05-23 21:13:36 +00:00
c9872a2575
* hmx-mm: update debug logging in hmx-mm * hmx-mm: update dequant logic to use HVX_vector_x2/4 * hmx-mm: remove non-pipelined version of the quantize matmul It seems that we don't reall need non-pipelined version * hmx-mm: use activation depth mode and update naming Co-authored-by: Kim-Chyan Gan <kgan@qti.qualcomm.com> * hex-mm: minor hmx matmul naming updates * hmx-mm: remove unused vars * snapdragon: scripts bump default ubatch-size to 1K * hexagon: combine HMX and power and clock settings into a single set_power call * hmx-mm: remove leftover of the scale repl helper * hexagon: fix editconf error --------- Co-authored-by: Kim-Chyan Gan <kgan@qti.qualcomm.com>
49 lines
1.1 KiB
Bash
Executable file
49 lines
1.1 KiB
Bash
Executable file
#!/bin/sh
|
|
#
|
|
|
|
# Basedir on device
|
|
basedir=/data/local/tmp/llama.cpp
|
|
|
|
branch=.
|
|
[ "$B" != "" ] && branch=$B
|
|
|
|
adbserial=
|
|
[ "$S" != "" ] && adbserial="-s $S"
|
|
|
|
adbhost=
|
|
[ "$H" != "" ] && adbhost="-H $H"
|
|
|
|
model="Llama-3.2-3B-Instruct-Q4_0.gguf"
|
|
[ "$M" != "" ] && model="$M"
|
|
|
|
device="HTP0"
|
|
[ "$D" != "" ] && device="$D"
|
|
|
|
verbose=
|
|
[ "$V" != "" ] && verbose="GGML_HEXAGON_VERBOSE=$V" cli_opts="$cli_opts -v"
|
|
|
|
profile=
|
|
[ "$PROF" != "" ] && profile="GGML_HEXAGON_PROFILE=$PROF" cli_opts="$cli_opts -v"
|
|
|
|
opmask=
|
|
[ "$OPSTAGE" != "" ] && opmask="GGML_HEXAGON_OPSTAGE=$OPSTAGE"
|
|
|
|
nhvx=
|
|
[ "$NHVX" != "" ] && nhvx="GGML_HEXAGON_NHVX=$NHVX"
|
|
|
|
ndev=
|
|
[ "$NDEV" != "" ] && ndev="GGML_HEXAGON_NDEV=$NDEV"
|
|
|
|
hb=
|
|
[ "$HB" != "" ] && hb="GGML_HEXAGON_HOSTBUF=$HB"
|
|
|
|
set -x
|
|
|
|
adb $adbserial $adbhost shell " \
|
|
cd $basedir; \
|
|
LD_LIBRARY_PATH=$basedir/$branch/lib \
|
|
ADSP_LIBRARY_PATH=$basedir/$branch/lib \
|
|
$ndev $nhvx $opmask $verbose $profile $hb ./$branch/bin/llama-bench --device $device --mmap 0 -m $basedir/../gguf/$model \
|
|
--poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 \
|
|
--ubatch-size 1024 -fa 1 -ngl 99 $cli_opts $@ \
|
|
"
|