Commit 6b9ba4f2e for llama.cpp
commit 6b9ba4f2e8c1436511956f0b3c309e2c9e642071
Author: Georgi Gerganov <ggerganov@gmail.com>
Date: Sat Oct 24 09:21:24 2026 +0300
ci : fix data race between runners sharing the model cache (#31046)
* ci : fix data race between runners sharing the model cache
Two runners per mac mini share HOME, so concurrent jobs corrupt each
other downloads, converted models and venv under the shared MNT cache.
- gg_wget: download in a temp dir, publish with mv, so readers only
ever see complete files (-N cannot be combined with -O)
- convert, quantize and wikitext unzip now produce under a per-runner
scratch dir in OUT, published to MNT via hardlink when missing
- gguf-split and quantize tests get a per-runner TMP_DIR
- python venv moved from MNT to OUT
- metal, vulkan and webgpu mac jobs pass a per-runner OUT path
Assisted-by: dsh:llama.cpp/agent-qwen4 (RTX 5090 machine)
* ci : clean up scratch models after tests
Assisted-by: dsh:llama.cpp/agent-qwen4 (RTX 5090 machine)
* ci : fix q4_0 publish when a cached model exists
cp -n skips an existing file with exit code 1, so the ln fallback
aborted the qwen3 job under set -e. Publish through a unique temp
file with an atomic mv: readers never see a partial file and a
stale cached q4_0 gets replaced.
Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (RTX 5090 machine)
* ci : cache-first gg_wget to avoid re-downloads
HF sends no Last-Modified, so wget -N re-downloads the full files on
every run. Skip the download when a non-empty cache file exists: the
HF CI artifacts are static. Downloads still go through a temp dir and
an atomic mv, so concurrent runners never read partial files.
Assisted-by: dsh:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (RTX 5090 machine)
diff --git a/.github/workflows/ci-self-hosted-metal.yml b/.github/workflows/ci-self-hosted-metal.yml
index 5eb20096a..226bc8f6d 100644
--- a/.github/workflows/ci-self-hosted-metal.yml
+++ b/.github/workflows/ci-self-hosted-metal.yml
@@ -60,4 +60,4 @@ jobs:
- name: Test
id: ggml-ci
run: |
- GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+ GG_BUILD_METAL=1 bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
diff --git a/.github/workflows/ci-self-hosted-vulkan.yml b/.github/workflows/ci-self-hosted-vulkan.yml
index e651f2d1d..de888b1f6 100644
--- a/.github/workflows/ci-self-hosted-vulkan.yml
+++ b/.github/workflows/ci-self-hosted-vulkan.yml
@@ -150,7 +150,7 @@ jobs:
id: ggml-ci
run: |
vulkaninfo --summary
- GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+ GG_BUILD_VULKAN=1 bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
gpu-vulkan-intel-linux:
runs-on: [self-hosted, Linux, Intel]
diff --git a/.github/workflows/ci-self-hosted-webgpu.yml b/.github/workflows/ci-self-hosted-webgpu.yml
index 316ed33b9..f94689006 100644
--- a/.github/workflows/ci-self-hosted-webgpu.yml
+++ b/.github/workflows/ci-self-hosted-webgpu.yml
@@ -131,4 +131,4 @@ jobs:
id: ggml-ci
run: |
GG_BUILD_WEBGPU=1 GG_BUILD_WEBGPU_DAWN_PREFIX="$GITHUB_WORKSPACE/dawn" \
- bash ./ci/run.sh ~/results/llama.cpp ~/mnt/llama.cpp
+ bash ./ci/run.sh ~/results/llama.cpp/$RUNNER_NAME ~/mnt/llama.cpp
diff --git a/ci/run.sh b/ci/run.sh
index e3ffdb8af..4d75c7f17 100755
--- a/ci/run.sh
+++ b/ci/run.sh
@@ -185,18 +185,28 @@ fi
## helpers
-# download a file if it does not exist or if it is outdated
+# download a file unless already cached in $MNT
function gg_wget {
local out=$1
local url=$2
local cwd=`pwd`
+ local name=`basename $url`
+ local tmp=.gg-wget.$$.tmp
mkdir -p $out
cd $out
- # should not re-download if file is the same
- wget -nv -c -N $url
+ # cache first: HF artifacts are static, HF sends no Last-Modified for -N
+ if [ ! -s $name ]; then
+ # publish with mv: concurrent runners never read partial files
+ rm -rf $tmp && mkdir $tmp
+ (cd $tmp && wget -nv $url)
+ if [ -s $tmp/$name ]; then
+ mv -f $tmp/$name $name
+ fi
+ rm -rf $tmp
+ fi
cd $cwd
}
@@ -312,8 +322,8 @@ function gg_run_test_scripts {
set -e
- (cd ./tools/gguf-split && time bash tests.sh "$SRC/build-ci-release/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
- (cd ./tools/quantize && time bash tests.sh "$SRC/build-ci-release/bin" "$MNT/models") 2>&1 | tee -a $OUT/${ci}-scripts.log
+ (cd ./tools/gguf-split && time bash tests.sh "$SRC/build-ci-release/bin" "$OUT/scratch") 2>&1 | tee -a $OUT/${ci}-scripts.log
+ (cd ./tools/quantize && time bash tests.sh "$SRC/build-ci-release/bin" "$OUT/scratch") 2>&1 | tee -a $OUT/${ci}-scripts.log
set +e
}
@@ -374,10 +384,14 @@ function gg_run_qwen3_0_6b {
gg_wget models-mnt/wikitext/ https://huggingface.co/datasets/ggml-org/ci/resolve/main/wikitext-2-raw-v1.zip
- unzip -o models-mnt/wikitext/wikitext-2-raw-v1.zip -d models-mnt/wikitext/
+
+ rm -rf $OUT/scratch/qwen3-0.6B $OUT/scratch/wikitext
+ mkdir -p $OUT/scratch/qwen3-0.6B
+ unzip -o models-mnt/wikitext/wikitext-2-raw-v1.zip -d $OUT/scratch/wikitext/
path_models="../models-mnt/qwen3/0.6B"
- path_wiki="../models-mnt/wikitext/wikitext-2-raw"
+ path_local="$OUT/scratch/qwen3-0.6B"
+ path_wiki="$OUT/scratch/wikitext/wikitext-2-raw"
rm -rf build-ci-release && mkdir build-ci-release && cd build-ci-release
@@ -386,64 +400,59 @@ function gg_run_qwen3_0_6b {
(cmake -G "${CMAKE_GENERATOR}" -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
(time cmake --build . --config Release -j$(nproc)) 2>&1 | tee -a $OUT/${ci}-make.log
- python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf --outtype f16
- python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_models}/ggml-model-bf16.gguf --outtype bf16
-
- model_f16="${path_models}/ggml-model-f16.gguf"
- model_bf16="${path_models}/ggml-model-bf16.gguf"
- model_q8_0="${path_models}/ggml-model-q8_0.gguf"
- model_q4_0="${path_models}/ggml-model-q4_0.gguf"
- model_q4_1="${path_models}/ggml-model-q4_1.gguf"
- model_q5_0="${path_models}/ggml-model-q5_0.gguf"
- model_q5_1="${path_models}/ggml-model-q5_1.gguf"
- model_q2_k="${path_models}/ggml-model-q2_k.gguf"
- model_q3_k="${path_models}/ggml-model-q3_k.gguf"
- model_q4_k="${path_models}/ggml-model-q4_k.gguf"
- model_q5_k="${path_models}/ggml-model-q5_k.gguf"
- model_q6_k="${path_models}/ggml-model-q6_k.gguf"
+ python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_local}/ggml-model-f16.gguf --outtype f16
+ python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_local}/ggml-model-bf16.gguf --outtype bf16
+
+ model_f16="${path_local}/ggml-model-f16.gguf"
+ model_bf16="${path_local}/ggml-model-bf16.gguf"
+ model_q4_0="${path_local}/ggml-model-q4_0.gguf"
wiki_test="${path_wiki}/wiki.test.raw"
- ./bin/llama-quantize ${model_bf16} ${model_q8_0} q8_0 $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q4_0} q4_0 $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q4_1} q4_1 $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q5_0} q5_0 $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q5_1} q5_1 $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q2_k} q2_k $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q3_k} q3_k $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q4_k} q4_k $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q5_k} q5_k $(nproc)
- ./bin/llama-quantize ${model_bf16} ${model_q6_k} q6_k $(nproc)
+ function check_ppl {
+ qnt="$1"
+ ppl=$(echo "$2" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1)
+
+ if [ $(echo "$ppl > 20.0" | bc) -eq 1 ]; then
+ printf ' - %s @ %s (FAIL: ppl > 20.0)\n' "$qnt" "$ppl"
+ return 20
+ fi
+
+ printf ' - %s @ %s OK\n' "$qnt" "$ppl"
+ return 0
+ }
+
+ for qnt in q8_0 q4_0 q4_1 q5_0 q5_1 q2_k q3_k q4_k q5_k q6_k; do
+ model="${path_local}/ggml-model-${qnt}.gguf"
+
+ ./bin/llama-quantize ${model_bf16} ${model} ${qnt} $(nproc)
+
+ (time ./bin/llama-completion -no-cnv --model ${model} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-${qnt}.log
+ (time ./bin/llama-perplexity --model ${model} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-${qnt}.log
+
+ # note: ppl > 20.0 for q2_k with this model
+ if [ "${qnt}" != "q2_k" ]; then
+ check_ppl "${qnt}" "$(cat $OUT/${ci}-tg-${qnt}.log | grep "^\[1\]")"
+ fi
+
+ if [ "${qnt}" = "q4_0" ]; then
+ # q4_0 is kept for other tests
+ q4_0="${path_models}/ggml-model-q4_0.gguf"
+ ln ${model} "$q4_0" 2>/dev/null || { cp ${model} $q4_0.tmp.$$ && mv -f $q4_0.tmp.$$ $q4_0; }
+ else
+ rm -f ${model}
+ fi
+ done
(time ./bin/llama-fit-params --model ${model_f16} 2>&1 | tee -a $OUT/${ci}-fp-f16.log)
(time ./bin/llama-completion -no-cnv --model ${model_f16} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log
(time ./bin/llama-completion -no-cnv --model ${model_bf16} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-bf16.log
- (time ./bin/llama-completion -no-cnv --model ${model_q8_0} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log
- (time ./bin/llama-completion -no-cnv --model ${model_q4_0} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log
- (time ./bin/llama-completion -no-cnv --model ${model_q4_1} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log
- (time ./bin/llama-completion -no-cnv --model ${model_q5_0} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log
- (time ./bin/llama-completion -no-cnv --model ${model_q5_1} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log
- (time ./bin/llama-completion -no-cnv --model ${model_q2_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log
- (time ./bin/llama-completion -no-cnv --model ${model_q3_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log
- (time ./bin/llama-completion -no-cnv --model ${model_q4_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log
- (time ./bin/llama-completion -no-cnv --model ${model_q5_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log
- (time ./bin/llama-completion -no-cnv --model ${model_q6_k} -ngl 99 -c 1024 -s 1234 -n 64 --ignore-eos -p "I believe the meaning of life is" ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log
(time ./bin/llama-perplexity --model ${model_f16} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-f16.log
if [ -z ${GG_BUILD_NO_BF16} ]; then
(time ./bin/llama-perplexity --model ${model_bf16} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-bf16.log
fi
- (time ./bin/llama-perplexity --model ${model_q8_0} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log
- (time ./bin/llama-perplexity --model ${model_q4_0} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_0.log
- (time ./bin/llama-perplexity --model ${model_q4_1} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_1.log
- (time ./bin/llama-perplexity --model ${model_q5_0} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_0.log
- (time ./bin/llama-perplexity --model ${model_q5_1} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_1.log
- (time ./bin/llama-perplexity --model ${model_q2_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q2_k.log
- (time ./bin/llama-perplexity --model ${model_q3_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q3_k.log
- (time ./bin/llama-perplexity --model ${model_q4_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q4_k.log
- (time ./bin/llama-perplexity --model ${model_q5_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q5_k.log
- (time ./bin/llama-perplexity --model ${model_q6_k} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-tg-q6_k.log
(time ./bin/llama-imatrix --model ${model_f16} -f ${wiki_test} -ngl 99 -c 1024 -b 512 --chunks 2 ) 2>&1 | tee -a $OUT/${ci}-imatrix.log
@@ -456,33 +465,13 @@ function gg_run_qwen3_0_6b {
(time ./bin/test-llama-context --model ${model_q4_0} -ngl 99 -c 1024 -fa on ) 2>&1 | tee -a $OUT/${ci}-test-llama-context.log
fi
- function check_ppl {
- qnt="$1"
- ppl=$(echo "$2" | grep -oE "[0-9]+\.[0-9]+" | tail -n 1)
-
- if [ $(echo "$ppl > 20.0" | bc) -eq 1 ]; then
- printf ' - %s @ %s (FAIL: ppl > 20.0)\n' "$qnt" "$ppl"
- return 20
- fi
-
- printf ' - %s @ %s OK\n' "$qnt" "$ppl"
- return 0
- }
-
check_ppl "f16" "$(cat $OUT/${ci}-tg-f16.log | grep "^\[1\]")"
if [ -z ${GG_BUILD_NO_BF16} ]; then
check_ppl "bf16" "$(cat $OUT/${ci}-tg-bf16.log | grep "^\[1\]")"
fi
- check_ppl "q8_0" "$(cat $OUT/${ci}-tg-q8_0.log | grep "^\[1\]")"
- check_ppl "q4_0" "$(cat $OUT/${ci}-tg-q4_0.log | grep "^\[1\]")"
- check_ppl "q4_1" "$(cat $OUT/${ci}-tg-q4_1.log | grep "^\[1\]")"
- check_ppl "q5_0" "$(cat $OUT/${ci}-tg-q5_0.log | grep "^\[1\]")"
- check_ppl "q5_1" "$(cat $OUT/${ci}-tg-q5_1.log | grep "^\[1\]")"
- #check_ppl "q2_k" "$(cat $OUT/${ci}-tg-q2_k.log | grep "^\[1\]")" # note: ppl > 20.0 for this quant and model
- check_ppl "q3_k" "$(cat $OUT/${ci}-tg-q3_k.log | grep "^\[1\]")"
- check_ppl "q4_k" "$(cat $OUT/${ci}-tg-q4_k.log | grep "^\[1\]")"
- check_ppl "q5_k" "$(cat $OUT/${ci}-tg-q5_k.log | grep "^\[1\]")"
- check_ppl "q6_k" "$(cat $OUT/${ci}-tg-q6_k.log | grep "^\[1\]")"
+
+ # scratch is rebuilt on every run; q4_0 is already published to $MNT
+ rm -rf $OUT/scratch/qwen3-0.6B $OUT/scratch/wikitext
set +e
}
@@ -505,6 +494,8 @@ function gg_run_embd_bge_small {
gg_wget models-mnt/bge-small/1_Pooling https://huggingface.co/BAAI/bge-small-en-v1.5/raw/main/1_Pooling/config.json
path_models="../models-mnt/bge-small"
+ path_local="$OUT/scratch/bge-small"
+ rm -rf $path_local && mkdir -p $path_local
rm -rf build-ci-release && mkdir build-ci-release && cd build-ci-release
@@ -513,10 +504,10 @@ function gg_run_embd_bge_small {
(cmake -G "${CMAKE_GENERATOR}" -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
(time cmake --build . --config Release -j$(nproc)) 2>&1 | tee -a $OUT/${ci}-make.log
- python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
+ python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_local}/ggml-model-f16.gguf
- model_f16="${path_models}/ggml-model-f16.gguf"
- model_q8_0="${path_models}/ggml-model-q8_0.gguf"
+ model_f16="${path_local}/ggml-model-f16.gguf"
+ model_q8_0="${path_local}/ggml-model-q8_0.gguf"
./bin/llama-quantize ${model_f16} ${model_q8_0} q8_0
@@ -525,6 +516,8 @@ function gg_run_embd_bge_small {
(time ./bin/llama-embedding --model ${model_f16} -p "I believe the meaning of life is" -ngl 99 -c 0 --no-op-offload) 2>&1 | tee -a $OUT/${ci}-tg-f16.log
(time ./bin/llama-embedding --model ${model_q8_0} -p "I believe the meaning of life is" -ngl 99 -c 0 --no-op-offload) 2>&1 | tee -a $OUT/${ci}-tg-q8_0.log
+ rm -rf $path_local
+
set +e
}
@@ -541,6 +534,8 @@ function gg_run_rerank_tiny {
gg_wget models-mnt/rerank-tiny/ https://huggingface.co/jinaai/jina-reranker-v1-tiny-en/raw/main/vocab.json
path_models="../models-mnt/rerank-tiny"
+ path_local="$OUT/scratch/rerank-tiny"
+ rm -rf $path_local && mkdir -p $path_local
rm -rf build-ci-release && mkdir build-ci-release && cd build-ci-release
@@ -549,9 +544,9 @@ function gg_run_rerank_tiny {
(cmake -G "${CMAKE_GENERATOR}" -DCMAKE_BUILD_TYPE=Release ${CMAKE_EXTRA} .. ) 2>&1 | tee -a $OUT/${ci}-cmake.log
(time cmake --build . --config Release -j$(nproc)) 2>&1 | tee -a $OUT/${ci}-make.log
- python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_models}/ggml-model-f16.gguf
+ python3 ../convert_hf_to_gguf.py ${path_models} --outfile ${path_local}/ggml-model-f16.gguf
- model_f16="${path_models}/ggml-model-f16.gguf"
+ model_f16="${path_local}/ggml-model-f16.gguf"
(time ./bin/llama-fit-params --model ${model_f16} 2>&1 | tee -a $OUT/${ci}-fp-f16.log)
@@ -581,6 +576,8 @@ function gg_run_rerank_tiny {
check_score "rerank score 1" "$(cat $OUT/${ci}-rk-f16.log | grep "rerank score 1")" "0.00" "0.05" | tee -a $OUT/${ci}-rk-f16.log
check_score "rerank score 2" "$(cat $OUT/${ci}-rk-f16.log | grep "rerank score 2")" "0.10" "0.30" | tee -a $OUT/${ci}-rk-f16.log
+ rm -rf $path_local
+
set +e
}
@@ -687,11 +684,11 @@ if [ -z ${GG_BUILD_LOW_PERF} ]; then
ln -sfn ${mnt_models} ${SRC}/models-mnt
# Create a fresh python3 venv and enter it
- if ! python3 -m venv "$MNT/venv"; then
- echo "Error: Failed to create Python virtual environment at $MNT/venv."
+ if ! python3 -m venv "$OUT/venv"; then
+ echo "Error: Failed to create Python virtual environment at $OUT/venv."
exit 1
fi
- source "$MNT/venv/bin/activate"
+ source "$OUT/venv/bin/activate"
pip install -r ${SRC}/requirements.txt --disable-pip-version-check
pip install --editable gguf-py --disable-pip-version-check