ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : move end-user examples to tools directory (#13249)

Browse source 
* llama : move end-user examples to tools directory

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
This commit is contained in:
Diego Devesa 2025-05-02 20:27:13 +02:00 • committed by GitHub
parent b34443923c
commit 1d36b3670b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
213 changed files with 226 additions and 190 deletions
Download patch file Download diff file Expand all files Collapse all files

89
tools/gguf-split/tests.sh Executable file
View file

@ -0,0 +1,89 @@
#!/bin/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=$1/llama-cli
WORK_PATH=$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/gemma-1.1-2b-it-Q8_0-GGUF --file gemma-1.1-2b-it.Q8_0.gguf
)
echo PASS
# 2. Split with max tensors strategy
$SPLIT --split-max-tensors 28 $WORK_PATH/gemma-1.1-2b-it.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-00006.gguf --n-predict 32
echo PASS
echo
# 3. Merge
$SPLIT --merge $WORK_PATH/ggml-model-split-00001-of-00006.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 --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 $WORK_PATH/ggml-model-split-32-tensors-00001-of-00007.gguf --n-predict 32
echo PASS
echo
# 5. Merge
#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00006.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 2G $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-2G
echo PASS
echo
# 6b. Test the sharded model is loading properly
$MAIN -no-cnv --model $WORK_PATH/ggml-model-split-2G-00001-of-00002.gguf --n-predict 32
echo PASS
echo
# Clean up
rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-merge*.gguf