mirror of
https://github.com/ggerganov/llama.cpp
synced 2026-03-05 14:49:45 +01:00
6c2131773c
* wip * wip * fix logging, add display info * handle commands * add args * wip * move old cli to llama-completion * rm deprecation notice * move server to a shared library * move ci to llama-completion * add loading animation * add --show-timings arg * add /read command, improve LOG_ERR * add args for speculative decoding, enable show timings by default * add arg --image and --audio * fix windows build * support reasoning_content * fix llama2c workflow * color default is auto * fix merge conflicts * properly fix color problem Co-authored-by: bandoti <bandoti@users.noreply.github.com> * better loading spinner * make sure to clean color on force-exit * also clear input files on "/clear" * simplify common_log_flush * add warning in mtmd-cli * implement console writter * fix data race * add attribute * fix llama-completion and mtmd-cli * add some notes about console::log * fix compilation --------- Co-authored-by: bandoti <bandoti@users.noreply.github.com>
90 lines
2.3 KiB
Bash
Executable File
90 lines
2.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -eu
|
|
|
|
if [ $# -lt 1 ]
|
|
then
|
|
echo "usage: $0 path_to_build_binary [path_to_temp_folder]"
|
|
echo "example: $0 ../../build/bin ../../tmp"
|
|
exit 1
|
|
fi
|
|
|
|
if [ $# -gt 1 ]
|
|
then
|
|
TMP_DIR=$2
|
|
else
|
|
TMP_DIR=/tmp
|
|
fi
|
|
|
|
set -x
|
|
|
|
SPLIT=$1/llama-gguf-split
|
|
MAIN=$1/llama-completion
|
|
WORK_PATH=$TMP_DIR/gguf-split
|
|
ROOT_DIR=$(realpath $(dirname $0)/../../)
|
|
|
|
mkdir -p "$WORK_PATH"
|
|
|
|
# Clean up in case of previously failed test
|
|
rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-merge*.gguf
|
|
|
|
# 1. Get a model
|
|
(
|
|
cd $WORK_PATH
|
|
"$ROOT_DIR"/scripts/hf.sh --repo ggml-org/Qwen3-0.6B-GGUF --file Qwen3-0.6B-Q8_0.gguf
|
|
)
|
|
echo PASS
|
|
|
|
# 2. Split with max tensors strategy
|
|
$SPLIT --split-max-tensors 28 $WORK_PATH/Qwen3-0.6B-Q8_0.gguf $WORK_PATH/ggml-model-split
|
|
echo PASS
|
|
echo
|
|
|
|
# 2b. Test the sharded model is loading properly
|
|
$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-00001-of-00012.gguf -p "I believe the meaning of life is" --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# 3. Merge
|
|
$SPLIT --merge $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-merge.gguf
|
|
echo PASS
|
|
echo
|
|
|
|
# 3b. Test the merged model is loading properly
|
|
$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge.gguf -p "I believe the meaning of life is" --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# 4. Split with no tensors in the first split
|
|
$SPLIT --split-max-tensors 32 --no-tensor-first-split $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-32-tensors
|
|
echo PASS
|
|
echo
|
|
|
|
# 4b. Test the sharded model is loading properly
|
|
$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-32-tensors-00001-of-00011.gguf -p "I believe the meaning of life is" --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# 5. Merge
|
|
#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00012.gguf $WORK_PATH/ggml-model-merge-2.gguf
|
|
#echo PASS
|
|
#echo
|
|
|
|
# 5b. Test the merged model is loading properly
|
|
#$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge-2.gguf --n-predict 32
|
|
#echo PASS
|
|
#echo
|
|
|
|
# 6. Split with size strategy
|
|
$SPLIT --split-max-size 500M $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-500M
|
|
echo PASS
|
|
echo
|
|
|
|
# 6b. Test the sharded model is loading properly
|
|
$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-500M-00001-of-00002.gguf -p "I believe the meaning of life is" --n-predict 32
|
|
echo PASS
|
|
echo
|
|
|
|
# Clean up
|
|
rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-merge*.gguf
|