Sync from upstream llama.cpp repository

2026-01-16 10:43:34 +08:00
parent 3bc369a6f7
commit f4ae4cc7da
2053 changed files with 956010 additions and 1 deletions
--- a/scripts/snapdragon/adb/llama-cli.farf
+++ b/scripts/snapdragon/adb/llama-cli.farf
@@ -0,0 +1 @@
+0xffff
--- a/scripts/snapdragon/adb/run-bench.sh
+++ b/scripts/snapdragon/adb/run-bench.sh
@@ -0,0 +1,52 @@
+#!/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 \
+        --batch-size 128 -ngl 99 $cli_opts $@ \
+"
--- a/scripts/snapdragon/adb/run-cli.sh
+++ b/scripts/snapdragon/adb/run-cli.sh
@@ -0,0 +1,59 @@
+#!/bin/sh
+#
+
+# Basedir on device
+basedir=/data/local/tmp/llama.cpp
+
+cli_opts=
+
+branch=.
+[ "$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 --batch-size 128 -fa on \
+         -ngl 99 --device $device $cli_opts $@   \
+"
--- a/scripts/snapdragon/adb/run-completion.sh
+++ b/scripts/snapdragon/adb/run-completion.sh
@@ -0,0 +1,59 @@
+#!/bin/sh
+#
+
+# Basedir on device
+basedir=/data/local/tmp/llama.cpp
+
+cli_opts=
+
+branch=.
+[ "$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-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 $@   \
+"
--- a/scripts/snapdragon/adb/run-mtmd.sh
+++ b/scripts/snapdragon/adb/run-mtmd.sh
@@ -0,0 +1,68 @@
+#!/bin/sh
+#
+
+# Basedir on device
+basedir=/data/local/tmp/llama.cpp
+
+cli_opts=
+
+branch=.
+[ "$B" != "" ] && branch=$B
+
+adbserial=
+[ "$S" != "" ] && adbserial="-s $S"
+
+adbhost=
+[ "$H" != "" ] && adbhost="-H $H"
+
+model="gemma-3-4b-it-Q4_0.gguf"
+[ "$M" != "" ] && model="$M"
+
+mmproj="mmproj-F16.gguf"
+[ "$MMPROJ" != "" ] && mmproj="$MMPROJ"
+
+image=
+[ "$IMG" != "" ] && image="$IMG"
+
+device="HTP0"
+[ "$D" != "" ] && device="$D"
+
+verbose=
+[ "$V" != "" ] && verbose="GGML_HEXAGON_VERBOSE=$V"
+
+experimental="GGML_HEXAGON_EXPERIMENTAL=1"
+[ "$E" != "" ] && experimental="GGML_HEXAGON_EXPERIMENTAL=$E"
+
+sched=
+[ "$SCHED" != "" ] && sched="GGML_SCHED_DEBUG=2" cli_opts="$cli_opts -v"
+
+profile=
+[ "$PROF" != "" ] && profile="GGML_HEXAGON_PROFILE=$PROF GGML_HEXAGON_OPSYNC=1"
+
+opmask=
+[ "$OPMASK" != "" ] && opmask="GGML_HEXAGON_OPMASK=$OPMASK"
+
+nhvx=
+[ "$NHVX" != "" ] && nhvx="GGML_HEXAGON_NHVX=$NHVX"
+
+ndev=
+[ "$NDEV" != "" ] && ndev="GGML_HEXAGON_NDEV=$NDEV"
+
+# MTMD backend device for vision model (defaults to CPU if not set)
+mtmd_backend=
+[ "$MTMD_DEVICE" != "" ] && mtmd_backend="MTMD_BACKEND_DEVICE=$MTMD_DEVICE"
+
+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 $mtmd_backend       \
+      ./$branch/bin/llama-mtmd-cli --no-mmap -m $basedir/../gguf/$model   \
+         --mmproj $basedir/../gguf/$mmproj \
+         --image $basedir/../gguf/$image \
+         --poll 1000 -t 6 --cpu-mask 0xfc --cpu-strict 1             \
+         --ctx-size 8192 --batch-size 128 -ctk q8_0 -ctv q8_0 -fa on \
+         -ngl 99 --device $device -v $cli_opts $@ \
+"
--- a/scripts/snapdragon/adb/run-tool.sh
+++ b/scripts/snapdragon/adb/run-tool.sh
@@ -0,0 +1,54 @@
+#!/bin/sh
+#
+
+# Basedir on device
+basedir=/data/local/tmp/llama.cpp
+
+cli_opts=
+
+branch=.
+[ "$B" != "" ] && branch=$B
+
+adbserial=
+[ "$S" != "" ] && adbserial="-s $S"
+
+adbhost=
+[ "$H" != "" ] && adbhost="-H $H"
+
+device="HTP0"
+[ "$D" != "" ] && device="$D"
+
+verbose=
+[ "$V" != "" ] && verbose="GGML_HEXAGON_VERBOSE=$V"
+
+experimental=
+[ "$E" != "" ] && experimental="GGML_HEXAGON_EXPERIMENTAL=$E"
+
+sched=
+[ "$SCHED" != "" ] && sched="GGML_SCHED_DEBUG=2" cli_opts="$cli_opts -v"
+
+profile=
+[ "$PROF" != "" ] && profile="GGML_HEXAGON_PROFILE=$PROF GGML_HEXAGON_OPSYNC=1"
+
+opmask=
+[ "$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
+
+tool=$1; shift
+
+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/$tool $@ \
+"