Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	CODEOWNERS
#	CONTRIBUTING.md
#	README.md
#	ci/run.sh
#	examples/embedding/README.md
#	tests/test-backend-ops.cpp
This commit is contained in:
Concedo
2025-09-22 21:25:29 +08:00
parent 59b6a09ae1 37a23c17bd
commit efe546390b
9 changed files with 395 additions and 206 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/gguf-split/tests.sh
+9 -9
View File
@@ -31,27 +31,27 @@ 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
"$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/gemma-1.1-2b-it.Q8_0.gguf $WORK_PATH/ggml-model-split
$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-00006.gguf --n-predict 32
$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-00006.gguf $WORK_PATH/ggml-model-merge.gguf
$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 --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-merge.gguf -p "I believe the meaning of life is" --n-predict 32
echo PASS
echo
@@ -61,12 +61,12 @@ 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
$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-00006.gguf $WORK_PATH/ggml-model-merge-2.gguf
#$SPLIT --merge $WORK_PATH/ggml-model-split-32-tensors-00001-of-00012.gguf $WORK_PATH/ggml-model-merge-2.gguf
#echo PASS
#echo
@@ -76,12 +76,12 @@ echo
#echo
# 6. Split with size strategy
$SPLIT --split-max-size 2G $WORK_PATH/ggml-model-merge.gguf $WORK_PATH/ggml-model-split-2G
$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-2G-00001-of-00002.gguf --n-predict 32
$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
tools/quantize/tests.sh
+6 -6
View File
@@ -32,32 +32,32 @@ rm -f $WORK_PATH/ggml-model-split*.gguf $WORK_PATH/ggml-model-requant*.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
"$ROOT_DIR"/scripts/hf.sh --repo ggml-org/Qwen3-0.6B-GGUF --file Qwen3-0.6B-Q8_0.gguf
)
echo PASS
# 2. Split model
$SPLIT --split-max-tensors 28 $WORK_PATH/gemma-1.1-2b-it.Q8_0.gguf $WORK_PATH/ggml-model-split
$SPLIT --split-max-tensors 28 $WORK_PATH/Qwen3-0.6B-Q8_0.gguf $WORK_PATH/ggml-model-split
echo PASS
echo
# 3. Requant model with '--keep-split'
$QUANTIZE --allow-requantize --keep-split $WORK_PATH/ggml-model-split-00001-of-00006.gguf $WORK_PATH/ggml-model-requant.gguf Q4_K
$QUANTIZE --allow-requantize --keep-split $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-requant.gguf Q4_K
echo PASS
echo
# 3a. Test the requanted model is loading properly
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-00001-of-00006.gguf --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-00001-of-00012.gguf -p "I believe the meaning of life is" --n-predict 32
echo PASS
echo
# 4. Requant mode without '--keep-split'
$QUANTIZE --allow-requantize $WORK_PATH/ggml-model-split-00001-of-00006.gguf $WORK_PATH/ggml-model-requant-merge.gguf Q4_K
$QUANTIZE --allow-requantize $WORK_PATH/ggml-model-split-00001-of-00012.gguf $WORK_PATH/ggml-model-requant-merge.gguf Q4_K
echo PASS
echo
# 4b. Test the requanted model is loading properly
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-merge.gguf --n-predict 32
$MAIN -no-cnv --model $WORK_PATH/ggml-model-requant-merge.gguf -p "I believe the meaning of life is" --n-predict 32
echo PASS
echo
tools/server/webui/src/lib/services/chat.ts
+3 -1
View File
@@ -264,12 +264,14 @@ export class ChatService {
let lastTimings: ChatMessageTimings | undefined;
try {
let chunk = '';
while (true) {
const { done, value } = await reader.read();
if (done) break;
const chunk = decoder.decode(value, { stream: true });
chunk += decoder.decode(value, { stream: true });
const lines = chunk.split('\n');
chunk = lines.pop() || ''; // Save incomplete line for next read
for (const line of lines) {
if (line.startsWith('data: ')) {