sync from b7516

scripts/snapdragon/adb/run-cli.sh

@@ -12,26 +12,23 @@ branch=.
 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"
+
 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="$cli_opts -v"
+[ "$PROF" != "" ] && profile="GGML_HEXAGON_PROFILE=$PROF GGML_HEXAGON_OPSYNC=1"
 
 opmask=
 [ "$OPMASK" != "" ] && opmask="GGML_HEXAGON_OPMASK=$OPMASK"
@@ -42,18 +39,15 @@ nhvx=
 ndev=
 [ "$NDEV" != "" ] && ndev="GGML_HEXAGON_NDEV=$NDEV"
 
-hb=
-[ "$HB" != "" ] && hb="GGML_HEXAGON_HOSTBUF=$HB"
-
 set -x
 
-adb $adbserial $adbhost shell " \
+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 $hb \
-      ./$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 $@   \
+    $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 -ctk q8_0 -ctv q8_0 -fa on \
+         -ngl 99 --device $device $cli_opts $@ \
 "