mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-08 12:10:25 +00:00
Max Krasnyansky
13e673863b
* hex-mm: fold mm quant tasks into the main matmul threads * hex-mm: minor formatting fixes * hex-mm: cleanup is_quant checks in dma dispatch * hex-mm: fix dst-spad alignment * hex-mm: move fp kernels in the hvx-mm-kernels header * hex-mm: fuse with ADD * hex-fa: factor out ukernels into separate headers and unify the rest * hex-fa: move kernel-params compute into the host * hex-fa: refactor vtcm alloc for consistency * hex-fa: add support for FA_SELECT * hex-fa: update tracing insrumentation to cover all functions * hex-fa: update hvx fallback thresholds to recover t/g regressions * hex-fa: update tracing instrumentation * hex-fa: improved tracing with additional events * hex-fa: optimize mask processing (fastdiv, etc) * hex-fa: improve mask dma caching * hmx-fa: change loop order to maximize mask cache hits * hex-fa: remove over instrumentation * hex-fa: breakdown QKV prep trace events * hmx-fa: further mask proc optimizations * hex-fa: mask broadcast is the common case, optimize for that * hex-fa: use aligned loads where possible * hex-fa: update loops to use uint32_t indices * hmx-fa: fold vtcm init into q prep task * hex-fa: update rest of the hmx funcs to use uint32_t * hmx-fa: fold build_d into the main softmax loop * hmx-fa: start kv dmas earlier * hmx-fa: start mask dma a bit earlier * hex-fa: precompute rows per task to avoid divs * hmx-fa: specialize fa_o_store for f16 and f32 * hmx-fa: prelim support for Sinks * hmx-fa: keep softmax accumulators in fp32 * hex-fa: add tanh_f16 and exp2_f16 and use that in FA * hex-fa: use fp16 math in the hvx kernel * hex-fa: avoid expensive float -> __fp16 cast for slopes and softcap * hex-fa: replace most vec_exp_f32 with vec_exp2_f16 * hmx-fa: vectorize sinks update * hex-fa: minor formatting * hmx-fa: fold softcap loop into the tile load * hmx-fa: use vectoralias to populate sinks * hex-fa: remove redudant check * hex-fa: fix vtcm size compute to use fp32 for accumulators * hex-mm: fix trailing spaces * hmx-fa: dont use -inf to init mask to avoid conversion overflows * hex-fa: no need to explicitly guard -inf in the f16->f32 converter now * hmx-fa: cleanup fa sinks handling * hex-mm: fixed src2 stride handling when mm is fused with add * hex-fa: make lto happy
73 lines
1.4 KiB
Bash
Executable File
73 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 $H"
|
|
|
|
device="HTP0"
|
|
[ "$D" != "" ] && device="$D"
|
|
|
|
verbose=
|
|
[ "$V" != "" ] && verbose="GGML_HEXAGON_VERBOSE=$V"
|
|
|
|
sched=
|
|
[ "$SCHED" != "" ] && sched="GGML_SCHED_DEBUG=2" cli_opts="$cli_opts -v"
|
|
|
|
profile=
|
|
[ "$PROF" != "" ] && profile="GGML_HEXAGON_PROFILE=$PROF"
|
|
|
|
opmask=
|
|
[ "$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=$OP"
|
|
|
|
opfuse=
|
|
[ "$OC" != "" ] && opfuse="GGML_HEXAGON_OPFUSION=$OC"
|
|
|
|
mmsel=
|
|
[ "$MM" != "" ] && mmsel="GGML_HEXAGON_MM_SELECT=$MM"
|
|
|
|
fasel=
|
|
[ "$FA" != "" ] && fasel="GGML_HEXAGON_FA_SELECT=$FA"
|
|
|
|
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 $sched $opmask $profile $nhvx $hmx $ndev $hb $opbatch $opqueue $oppoll $opfuse $mmsel $fasel ./$branch/bin/$tool $@ \
|
|
"
|