mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-06-27 23:50:20 -05:00
aa50b2c2ae
* hex-mm: add support for Q4_1 matmul/matvec, hvx-only for now * hmx-mm: add support for Q4_1 * hex-mm: use Q8_1 dynamic quantization to avoid having to compute sums in the vec_dot * hexagon: fix repack scratch buffer overflow * hex-mm: fix Q4_1 repack buffer sizing * hexagon: flip the build order for mm and fa (seems to help LTO) * hex-mm: add vec_dot 4x1s and minor HMX cleanup after adding Q4_1 * hex-mm: fix fp16 vec_dot fallback to 2x1 and another issue that could cause incorrect output * hexagon: resurrect early-wake and add support for polling for op-batch completions With Q4_1 ggml-hexagon now claims pretty much the entire graphs which gives the CPU more time to chilax. This is a good thing! But it does add extra latency for the pure benchmark runs. Early wakeup helps recover the latency a bit in the normals runs and op-batch polling is just for benchmarking. --------- Co-authored-by: Todor Boinovski <todorb@qti.qualcomm.com>
78 lines
1.8 KiB
Bash
Executable File
78 lines
1.8 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 $S"
|
|
|
|
adbhost=
|
|
[ "$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"
|
|
|
|
sched=
|
|
[ "$SCHED" != "" ] && sched="GGML_SCHED_DEBUG=2" cli_opts="$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=$NHVX"
|
|
|
|
hmx=
|
|
[ "$HMX" != "" ] && hmx="GGML_HEXAGON_USE_HMX=$HMX"
|
|
|
|
ndev=
|
|
[ "$NDEV" != "" ] && ndev="GGML_HEXAGON_NDEV=$NDEV"
|
|
|
|
hb=
|
|
[ "$HB" != "" ] && hb="GGML_HEXAGON_HOSTBUF=$HB"
|
|
|
|
opbatch=
|
|
[ "$OB" != "" ] && opbatch="GGML_HEXAGON_OPBATCH=$OB"
|
|
|
|
opqueue=
|
|
[ "$OQ" != "" ] && opqueue="GGML_HEXAGON_OPQUEUE=$OQ"
|
|
|
|
oppoll=
|
|
[ "$OP" != "" ] && oppoll="GGML_HEXAGON_OPPOLL=$OP"
|
|
|
|
opflt=
|
|
[ "$OF" != "" ] && opflt="GGML_HEXAGON_OPFILTER=$OF"
|
|
|
|
vmem=
|
|
[ "$VM" != "" ] && vmem="GGML_HEXAGON_VMEM=$VM"
|
|
|
|
mbuf=
|
|
[ "$MB" != "" ] && mbuf="GGML_HEXAGON_MBUF=$MB"
|
|
|
|
set -x
|
|
|
|
adb $adbserial $adbhost shell " \
|
|
cd $basedir; ulimit -c unlimited; \
|
|
LD_LIBRARY_PATH=$basedir/$branch/lib \
|
|
ADSP_LIBRARY_PATH=$basedir/$branch/lib \
|
|
$verbose $sched $opmask $profile $nhvx $hmx $ndev $hb $opbatch $opqueue $oppoll $opflt $vmem $mbuf \
|
|
./$branch/bin/llama-completion --no-mmap -m $basedir/../gguf/$model \
|
|
--poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 \
|
|
--ctx-size 8192 --ubatch-size 1024 -fa on \
|
|
-ngl 99 --device $device $cli_opts $@ \
|
|
"
|