Max Krasnyansky
7cadbfce10
* hex-dma: make chained dma the default to handle newer models This also includes some new instrumentation that we can remove later. * hexagon: add uint32 dump helper * hexagon: use single-page VTCM allocation to avoid issues with large gather ops in ssm-conv ssm-conv uses HVX gather instruction and that instruction cannot handle cases where the base+offset spans page boundaries. * hexagon: update ssm-conv to make base-addr compute a bit easier to read * hex-dma: use 1d mode for reshaping, it supports sizes up to 24-bits (>16MB) * hex-bin: fix incorrect stride logic * hexagon: make sure repack buffs are dumped for verbose > 2 * hex-bin: consistently use dma_queue_push even for dummy dst transactions * hex-dma: start using 2d-wide mode on v75 and up The removes the need to deal with the 16-bit limitaion for the strides. * hex-bin: cleanup kernel selection logic * hex-bin: cleanup binary op core and fix transposed tensor handling * snapdragon: update run-bench to use larger ubatch and fa-on
53 lines
1.2 KiB
Bash
Executable File
53 lines
1.2 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"
|
|
|
|
experimental=
|
|
[ "$E" != "" ] && experimental="GGML_HEXAGON_EXPERIMENTAL=$E"
|
|
|
|
profile=
|
|
[ "$PROF" != "" ] && profile="GGML_HEXAGON_PROFILE=$PROF GGML_HEXAGON_OPSYNC=1" cli_opts="$cli_opts -v"
|
|
|
|
opmask=
|
|
[ "$OPMASK" != "" ] && opmask="GGML_HEXAGON_OPMASK=$OPMASK"
|
|
|
|
nhvx=
|
|
[ "$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 $experimental $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 256 -fa 1 -ngl 99 $cli_opts $@ \
|
|
"
|