Merge commit '12ee1763a6f6130ce820a366d220bbadff54b818' into concedo_experimental

# Conflicts:
#	docs/backend/hexagon/README.md
#	docs/backend/hexagon/developer.md
#	examples/gen-docs/gen-docs.cpp
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	examples/sycl/run-llama2.sh
#	examples/sycl/run-llama3.sh
#	examples/sycl/win-run-llama2.bat
#	examples/sycl/win-run-llama3.bat
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-utils.h
#	ggml/src/ggml-hexagon/htp/act-ops.c
#	ggml/src/ggml-hexagon/htp/htp-dma.c
#	ggml/src/ggml-hexagon/htp/htp-dma.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-opencl/kernels/transpose.cl
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	scripts/snapdragon/adb/run-cli.sh
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2025-12-24 23:57:41 +08:00
21 changed files with 1325 additions and 21 deletions
+53
View File
@@ -0,0 +1,53 @@
#!/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="$D"
experimental=
[ "$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"
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 -fa on \
-ngl 99 -no-cnv --device $device $cli_opts $@ \
"