mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-02 13:19:27 +01:00
39fb81f875
* hexagon: refactor set/get/sum-rows ops to use local context * hexagon: refactor ROPE and Softmax Ops to use local context Improves performance a bit by precomputing things and saving in the context. * hexagon: refactor activation ops to use local context struct * hexagon: refactor unary ops to use local context struct and DMA/VTCM * hexagon: use aligned hvx_scale function * hexagon: remove unused fields from op_context * hexagon: rewrite ROPE to use DMA and VTCM scratchpad * hex-rope: keep N rows in scratchpad (instead of just two) * hex-rope: introduce rowidx cache * hex-rope: remove unused fields * hex-rope: rewrite dma prefetch logic to allow for multi-row fetch/compute also removes the need for fastdiv. * hex-rope: minor formatting * hex-rope: use indices and unroll the loops * hex-rope: more updates to cleanup rope-block handling * hexagon: cleanup supported type/dims checks * hexagon: all reduce funcs replicated across lanes There is no need to explicitly replicate the first value. * snapdragon: update adb and windows scripts to use ubatch-size 256 Updated Ops support handles larger ubatches.
60 lines
1.4 KiB
Bash
Executable File
60 lines
1.4 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="$D"
|
|
|
|
experimental=
|
|
[ "$E" != "" ] && experimental="GGML_HEXAGON_EXPERIMENTAL=$E"
|
|
|
|
verbose=
|
|
[ "$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 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 $basedir; ulimit -c unlimited; \
|
|
LD_LIBRARY_PATH=$basedir/$branch/lib \
|
|
ADSP_LIBRARY_PATH=$basedir/$branch/lib \
|
|
$verbose $experimental $sched $opmask $profile $nhvx $ndev $hb \
|
|
./$branch/bin/llama-cli --no-mmap -m $basedir/../gguf/$model \
|
|
--poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1 \
|
|
--ctx-size 8192 --ubatch-size 256 -fa on \
|
|
-ngl 99 --device $device $cli_opts $@ \
|
|
"
|