Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
58 commits
Select commit Hold shift + click to select a range
19e899c
scripts: n_depth for compare-llama-bench [no ci] (#13201)
JohannesGaessler Apr 29, 2025
a0f7016
rpc : fix cache directory initialization (#13188)
hbuxiaofei Apr 30, 2025
da84c04
docker : do not build tests (#13204)
ngxson Apr 30, 2025
5933e6f
arg : allow using -hf offline (#13202)
ngxson Apr 30, 2025
44cd8d9
feat(ggml-cpu): enable z17 compile (#13182)
taronaeo Apr 30, 2025
07c2e2f
convert : correct typo image_mean --> image_std (#13208)
ngxson Apr 30, 2025
4163137
ggml : fix ppc64le build (#13176)
shalinib-ibm Apr 30, 2025
e5007a5
vulkan: use uint array index to avoid glslang bug (#13193)
jeffbolznv Apr 30, 2025
3b127c7
common : add -jf / --json-schema-file flag (#12011)
ochafik Apr 30, 2025
ceda28e
llava : remove duplicate include (#13207)
tattn Apr 30, 2025
3e168be
convert : improve model arch handling (#13122)
ngxson Apr 30, 2025
16a457f
fix typo: `n_ctx_pre_seq` -> `n_ctx_per_seq` (#13221)
ddh0 Apr 30, 2025
6f67cf1
arg : -hf do not fail if url mismatch (#13219)
ngxson Apr 30, 2025
e1e8e09
CUDA: batched+noncont MMQ, refactor bs>1 MoE code (#13199)
JohannesGaessler Apr 30, 2025
9998540
cuda : fix unused variable compile warning (whisper/0)
ggerganov Apr 24, 2025
4254bb4
ggml : fix ggml_gallocr_ptr type (ggml/1205)
slaren Apr 30, 2025
8d33d74
sync : ggml
ggerganov May 1, 2025
a70183e
llama-model : fix the reported size class for nomic-embed-text-v2-moe…
cebtenzzre May 1, 2025
13c9a33
arg : remove CURLINFO_EFFECTIVE_METHOD (#13228)
ngxson May 1, 2025
8936784
mtmd : add **vision** support for Mistral Small 3.1 (#13231)
ngxson May 1, 2025
b5769d9
ggml : suppress Windows compiler warnings (whisper/3075)
danbev Apr 29, 2025
99881f7
whisper : add check that target name exists (whisper/3103)
danbev May 1, 2025
b1dd4d0
sync : ggml
ggerganov May 1, 2025
b0ecbd4
test: non-cont. b in test-backend-ops -o MUL_MAT (#13187)
JohannesGaessler May 1, 2025
fc727bc
vulkan: Handle src1 batch dimension in non-contiguous mat-vec-mul sha…
jeffbolznv May 1, 2025
79f26e9
vulkan: Add bfloat16 support (#12554)
jeffbolznv May 1, 2025
e0f572c
llama-chat : update GLM4 chat template (#13238)
matteoserva May 1, 2025
b6e4ff6
clip : (minicpmv) Re-enable upscaling of images smaller than the CLIP…
lcarrere May 1, 2025
d7a14c4
build : fix build info on windows (#13239)
slaren May 1, 2025
f057808
ggml: Don't assert fail when tensor data changes (#13222)
jessegross May 1, 2025
8efbdad
rpc : avoid uninitialized memory in serialize_tensor (#13210)
justinsb May 1, 2025
d24d592
ci: fix cross-compile sync issues (#12804)
bandoti May 1, 2025
dcf8860
convert : explicitly disable trust_remote_code for AutoConfig (#13246)
ngxson May 2, 2025
fab647e
server : add cache reuse card link to help (#13230)
ggerganov May 2, 2025
e84773a
mtmd-cli : fix out_of_range when input image path is empty (#13244)
ahmedshakill May 2, 2025
2af6880
llama-chat : reset glmedge chat template (#13253)
piDack May 2, 2025
626083f
llama : plamo rope type is neox (#13260)
CISC May 2, 2025
cb06a3c
llama : orion rope type is neox (#13261)
CISC May 2, 2025
c642bc0
kv-cache : separate recurrent vs non-recurrent impl (#12799)
ggerganov May 2, 2025
074e42a
convert : converting mmproj for Qwen2/2.5VL from convert_hf_to_gguf (…
ngxson May 2, 2025
7d21234
convert : use correct context length for nomic-embed-text-v2 (#13216)
cebtenzzre May 2, 2025
2f56761
llama-model : support Qwen2 embedding models and pooling_mode_lasttok…
cebtenzzre May 2, 2025
3f3769b
ggml : Enable MMA for BF16 in llamafile_sgemm (#13148)
shalinib-ibm May 2, 2025
a75cb30
context : fix reorder logic (#13267)
ggerganov May 2, 2025
b344439
sync : ggml (#13268)
ggerganov May 2, 2025
1d36b36
llama : move end-user examples to tools directory (#13249)
slaren May 2, 2025
3bf785f
llama : Llama-3_1-Nemotron-Ultra-253B-v1 support (#12843)
ymcki May 3, 2025
36667c8
clip : revert the change of BOI/EOI token for GLM-edge (⚠️ breaking c…
ngxson May 3, 2025
3e959f0
imatrix: fix oob writes if src1 is not contiguous (#13286)
JohannesGaessler May 3, 2025
8ae5ebc
vulkan: Additional type support for unary, binary, and copy (#13266)
jeffbolznv May 4, 2025
8afbd96
CUDA: fix race condition in MMQ ids_dst (#13294)
JohannesGaessler May 4, 2025
93c4e23
CUDA: fix race condition in MMQ stream-k fixup (#13299)
JohannesGaessler May 4, 2025
9f2da58
llama : build windows releases with dl backends (#13220)
slaren May 4, 2025
86bd60d
llava/mtmd : fixes to fully support dl backends (#13303)
slaren May 4, 2025
6eb7d25
ggml : activate s390x simd for Q3_K (#13301)
taronaeo May 4, 2025
9fdfcda
rpc : use backend registry, support dl backends (#13304)
slaren May 4, 2025
27aa259
mtmd : add C public API (#13184)
ngxson May 4, 2025
a483ab2
Merge branch 'dev' into update-dev-from-master-2025-05-05-00-09
vansangpfiev May 5, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .devops/cpu.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -14,9 +14,9 @@ WORKDIR /app
COPY . .

RUN if [ "$TARGETARCH" = "amd64" ]; then \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON; \
elif [ "$TARGETARCH" = "arm64" ]; then \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DGGML_CPU_ARM_ARCH=${GGML_CPU_ARM_ARCH}; \
cmake -S . -B build -DCMAKE_BUILD_TYPE=Release -DGGML_NATIVE=OFF -DLLAMA_BUILD_TESTS=OFF -DGGML_CPU_ARM_ARCH=${GGML_CPU_ARM_ARCH}; \
else \
echo "Unsupported architecture"; \
exit 1; \
Expand Down
2 changes: 1 addition & 1 deletion .devops/cuda.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ COPY . .
RUN if [ "${CUDA_DOCKER_ARCH}" != "default" ]; then \
export CMAKE_ARGS="-DCMAKE_CUDA_ARCHITECTURES=${CUDA_DOCKER_ARCH}"; \
fi && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DLLAMA_CURL=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_CUDA=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
cmake --build build --config Release -j$(nproc)

RUN mkdir -p /app/lib && \
Expand Down
2 changes: 1 addition & 1 deletion .devops/intel.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -17,7 +17,7 @@ RUN if [ "${GGML_SYCL_F16}" = "ON" ]; then \
&& export OPT_SYCL_F16="-DGGML_SYCL_F16=ON"; \
fi && \
echo "Building with dynamic libs" && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DLLAMA_CURL=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON ${OPT_SYCL_F16} && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_SYCL=ON -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DLLAMA_BUILD_TESTS=OFF ${OPT_SYCL_F16} && \
cmake --build build --config Release -j$(nproc)

RUN mkdir -p /app/lib && \
Expand Down
2 changes: 1 addition & 1 deletion .devops/llama-cli-cann.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -22,7 +22,7 @@ ENV LD_LIBRARY_PATH=${ASCEND_TOOLKIT_HOME}/runtime/lib64/stub:$LD_LIBRARY_PATH

RUN echo "Building with static libs" && \
source /usr/local/Ascend/ascend-toolkit/set_env.sh --force && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_CANN=ON -DBUILD_SHARED_LIBS=OFF && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_CANN=ON -DBUILD_SHARED_LIBS=OFF -DLLAMA_BUILD_TESTS=OFF && \
cmake --build build --config Release --target llama-cli

# TODO: use image with NNRT
Expand Down
2 changes: 1 addition & 1 deletion .devops/musa.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ COPY . .
RUN if [ "${MUSA_DOCKER_ARCH}" != "default" ]; then \
export CMAKE_ARGS="-DMUSA_ARCHITECTURES=${MUSA_DOCKER_ARCH}"; \
fi && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_CURL=ON -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
cmake -B build -DGGML_NATIVE=OFF -DGGML_MUSA=ON -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON ${CMAKE_ARGS} -DCMAKE_EXE_LINKER_FLAGS=-Wl,--allow-shlib-undefined . && \
cmake --build build --config Release -j$(nproc)

RUN mkdir -p /app/lib && \
Expand Down
2 changes: 1 addition & 1 deletion .devops/rocm.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ WORKDIR /app
COPY . .

RUN HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \
cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=$ROCM_DOCKER_ARCH -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DCMAKE_BUILD_TYPE=Release -DLLAMA_CURL=ON \
cmake -S . -B build -DGGML_HIP=ON -DAMDGPU_TARGETS=$ROCM_DOCKER_ARCH -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON -DCMAKE_BUILD_TYPE=Release -DLLAMA_BUILD_TESTS=OFF \
&& cmake --build build --config Release -j$(nproc)

RUN mkdir -p /app/lib \
Expand Down
2 changes: 1 addition & 1 deletion .devops/vulkan.Dockerfile
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ WORKDIR /app

COPY . .

RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=1 -DLLAMA_CURL=1 -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON && \
RUN cmake -B build -DGGML_NATIVE=OFF -DGGML_VULKAN=1 -DLLAMA_BUILD_TESTS=OFF -DGGML_BACKEND_DL=ON -DGGML_CPU_ALL_VARIANTS=ON && \
cmake --build build --config Release -j$(nproc)

RUN mkdir -p /app/lib && \
Expand Down
8 changes: 4 additions & 4 deletions .editorconfig
Original file line number Diff line number Diff line change
Expand Up @@ -21,23 +21,23 @@ indent_style = tab
[prompts/*.txt]
insert_final_newline = unset

[examples/server/public/*]
[tools/server/public/*]
indent_size = 2

[examples/server/public/deps_*]
[tools/server/public/deps_*]
trim_trailing_whitespace = unset
indent_style = unset
indent_size = unset

[examples/server/deps_*]
[tools/server/deps_*]
trim_trailing_whitespace = unset
indent_style = unset
indent_size = unset

[examples/llama.swiftui/llama.swiftui.xcodeproj/*]
indent_style = tab

[examples/cvector-generator/*.txt]
[tools/cvector-generator/*.txt]
trim_trailing_whitespace = unset
insert_final_newline = unset

Expand Down
3 changes: 2 additions & 1 deletion .flake8
Original file line number Diff line number Diff line change
Expand Up @@ -2,8 +2,9 @@
max-line-length = 125
ignore = E203,E211,E221,E225,E231,E241,E251,E261,E266,E501,E701,E704,W503
exclude =
# Do not traverse examples
# Do not traverse examples and tools
examples,
tools,
# Do not include package initializers
__init__.py,
# No need to traverse our git directory
Expand Down
6 changes: 4 additions & 2 deletions .github/labeler.yml
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,9 @@ build:
- CMakePresets.json
examples:
- changed-files:
- any-glob-to-any-file: examples/**
- any-glob-to-any-file:
- examples/**
- tools/**
devops:
- changed-files:
- any-glob-to-any-file:
Expand All @@ -70,7 +72,7 @@ android:
server:
- changed-files:
- any-glob-to-any-file:
- examples/server/**
- tools/server/**
ggml:
- changed-files:
- any-glob-to-any-file:
Expand Down
30 changes: 15 additions & 15 deletions .github/workflows/bench.yml.disabled
Original file line number Diff line number Diff line change
Expand Up @@ -27,10 +27,10 @@ on:
push:
branches:
- master
paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'examples/server/*.h*', 'examples/server/*.cpp']
paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'tools/server/*.h*', 'tools/server/*.cpp']
pull_request_target:
types: [opened, synchronize, reopened]
paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'examples/server/*.h*', 'examples/server/*.cpp']
paths: ['llama.cpp', 'ggml.c', 'ggml-backend.cpp', 'ggml-quants.c', '**/*.cu', 'tools/server/*.h*', 'tools/server/*.cpp']
schedule:
- cron: '04 2 * * *'

Expand Down Expand Up @@ -69,7 +69,7 @@ jobs:
- name: Install python env
id: pipenv
run: |
cd examples/server/bench
cd tools/server/bench
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
Expand All @@ -79,7 +79,7 @@ jobs:
run: |
wget --quiet https://github.com/prometheus/prometheus/releases/download/v2.51.0/prometheus-2.51.0.linux-amd64.tar.gz
tar xzf prometheus*.tar.gz --strip-components=1
./prometheus --config.file=examples/server/bench/prometheus.yml &
./prometheus --config.file=tools/server/bench/prometheus.yml &
while ! nc -z localhost 9090; do
sleep 0.1
done
Expand All @@ -92,7 +92,7 @@ jobs:
- name: Install k6 and xk6-sse
id: k6_installation
run: |
cd examples/server/bench
cd tools/server/bench
go install go.k6.io/xk6/cmd/xk6@latest
xk6 build master \
--with github.com/phymbert/xk6-sse
Expand All @@ -116,7 +116,7 @@ jobs:
- name: Download the dataset
id: download_dataset
run: |
cd examples/server/bench
cd tools/server/bench
wget --quiet https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json

- name: Server bench
Expand All @@ -126,7 +126,7 @@ jobs:
run: |
set -eux

cd examples/server/bench
cd tools/server/bench
source venv/bin/activate
python bench.py \
--runner-label ${{ env.RUNNER_LABEL }} \
Expand Down Expand Up @@ -157,9 +157,9 @@ jobs:
name: bench-server-${{ github.job }}-${{ env.RUNNER_LABEL }}-${{ matrix.model }}-${{ matrix.ftype }}
compression-level: 9
path: |
examples/server/bench/*.jpg
examples/server/bench/*.json
examples/server/bench/*.log
tools/server/bench/*.jpg
tools/server/bench/*.json
tools/server/bench/*.log

- name: Commit status
uses: Sibz/github-status-action@v1
Expand All @@ -178,17 +178,17 @@ jobs:
with:
client_id: ${{secrets.IMGUR_CLIENT_ID}}
path: |
examples/server/bench/prompt_tokens_seconds.jpg
examples/server/bench/predicted_tokens_seconds.jpg
examples/server/bench/kv_cache_usage_ratio.jpg
examples/server/bench/requests_processing.jpg
tools/server/bench/prompt_tokens_seconds.jpg
tools/server/bench/predicted_tokens_seconds.jpg
tools/server/bench/kv_cache_usage_ratio.jpg
tools/server/bench/requests_processing.jpg

- name: Extract mermaid
id: set_mermaid
run: |
set -eux

cd examples/server/bench
cd tools/server/bench
PROMPT_TOKENS_SECONDS=$(cat prompt_tokens_seconds.mermaid)
echo "PROMPT_TOKENS_SECONDS<<EOF" >> $GITHUB_ENV
echo "$PROMPT_TOKENS_SECONDS" >> $GITHUB_ENV
Expand Down
66 changes: 42 additions & 24 deletions .github/workflows/build-linux-cross.yml
Original file line number Diff line number Diff line change
Expand Up @@ -4,18 +4,25 @@ on:
workflow_call:

jobs:
ubuntu-latest-riscv64-cpu-cross:
runs-on: ubuntu-latest
ubuntu-24-riscv64-cpu-cross:
runs-on: ubuntu-24.04

steps:
- uses: actions/checkout@v4
- name: Setup Riscv
run: |
sudo dpkg --add-architecture riscv64
sudo sed -i 's|http://azure.archive.ubuntu.com/ubuntu|http://ports.ubuntu.com/ubuntu-ports|g' \
/etc/apt/sources.list /etc/apt/apt-mirrors.txt
sudo apt-get clean
sudo apt-get update

# Add arch-specific repositories for non-amd64 architectures
cat << EOF | sudo tee /etc/apt/sources.list.d/riscv64-ports.list
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
EOF

sudo apt-get update || true ;# Prevent failure due to missing URLs.

sudo apt-get install -y --no-install-recommends \
build-essential \
gcc-14-riscv64-linux-gnu \
Expand All @@ -27,6 +34,7 @@ jobs:
cmake -B build -DCMAKE_BUILD_TYPE=Release \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=riscv64 \
Expand All @@ -40,21 +48,25 @@ jobs:

cmake --build build --config Release -j $(nproc)

ubuntu-latest-riscv64-vulkan-cross:
runs-on: ubuntu-latest
ubuntu-24-riscv64-vulkan-cross:
runs-on: ubuntu-24.04

steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0

- name: Setup Riscv
run: |
sudo dpkg --add-architecture riscv64
sudo sed -i 's|http://azure.archive.ubuntu.com/ubuntu|http://ports.ubuntu.com/ubuntu-ports|g' \
/etc/apt/sources.list /etc/apt/apt-mirrors.txt
sudo apt-get clean
sudo apt-get update

# Add arch-specific repositories for non-amd64 architectures
cat << EOF | sudo tee /etc/apt/sources.list.d/riscv64-ports.list
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
deb [arch=riscv64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
EOF

sudo apt-get update || true ;# Prevent failure due to missing URLs.

sudo apt-get install -y --no-install-recommends \
build-essential \
glslc \
Expand All @@ -69,6 +81,7 @@ jobs:
-DGGML_VULKAN=ON \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=riscv64 \
Expand All @@ -82,21 +95,25 @@ jobs:

cmake --build build --config Release -j $(nproc)

ubuntu-latest-arm64-vulkan-cross:
runs-on: ubuntu-latest
ubuntu-24-arm64-vulkan-cross:
runs-on: ubuntu-24.04

steps:
- uses: actions/checkout@v4
with:
fetch-depth: 0

- name: Setup Arm64
run: |
sudo dpkg --add-architecture arm64
sudo sed -i 's|http://azure.archive.ubuntu.com/ubuntu|http://ports.ubuntu.com/ubuntu-ports|g' \
/etc/apt/sources.list /etc/apt/apt-mirrors.txt
sudo apt-get clean
sudo apt-get update

# Add arch-specific repositories for non-amd64 architectures
cat << EOF | sudo tee /etc/apt/sources.list.d/arm64-ports.list
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble main universe
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-updates main universe
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-security main universe
deb [arch=arm64] http://ports.ubuntu.com/ubuntu-ports/ noble-backports main universe
EOF

sudo apt-get update || true ;# Prevent failure due to missing URLs.

sudo apt-get install -y --no-install-recommends \
build-essential \
glslc \
Expand All @@ -110,6 +127,7 @@ jobs:
-DGGML_VULKAN=ON \
-DGGML_OPENMP=OFF \
-DLLAMA_BUILD_EXAMPLES=ON \
-DLLAMA_BUILD_TOOLS=ON \
-DLLAMA_BUILD_TESTS=OFF \
-DCMAKE_SYSTEM_NAME=Linux \
-DCMAKE_SYSTEM_PROCESSOR=aarch64 \
Expand Down
Loading