Skip to content

opencl: use flat variants of q4_K and q6_K gemv for very large M (#24… #141

opencl: use flat variants of q4_K and q6_K gemv for very large M (#24…

opencl: use flat variants of q4_K and q6_K gemv for very large M (#24… #141

Workflow file for this run

name: Server
on:
workflow_dispatch: # allows manual triggering
inputs:
sha:
description: 'Commit SHA1 to build'
required: false
type: string
slow_tests:
description: 'Run slow tests'
required: true
type: boolean
push:
branches:
- master
paths: [
'.github/workflows/server.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
pull_request:
types: [opened, synchronize, reopened]
paths: [
'.github/workflows/server.yml',
'**/CMakeLists.txt',
'**/Makefile',
'**/*.h',
'**/*.hpp',
'**/*.c',
'**/*.cpp',
'**/*.cu',
'**/*.swift',
'**/*.m',
'tools/server/**.*'
]
env:
LLAMA_ARG_LOG_COLORS: 1
LLAMA_ARG_LOG_PREFIX: 1
LLAMA_ARG_LOG_TIMESTAMPS: 1
LLAMA_ARG_LOG_VERBOSITY: 10
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.run_id }}
cancel-in-progress: true
jobs:
ubuntu:
runs-on: ubuntu-24.04-arm
steps:
- name: Dependencies
id: depends
run: |
sudo apt-get update
sudo apt-get -y install \
build-essential \
xxd \
git \
cmake \
curl \
wget \
language-pack-en \
libssl-dev
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: server-ubuntu-24.04-arm
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
run: |
cmake -B build \
-DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Python setup
id: setup_python
uses: actions/setup-python@v6
with:
python-version: '3.11'
pip-install: -r tools/server/tests/requirements.txt
- name: Tests
id: server_integration_tests
run: |
cd tools/server/tests
pytest -v -x -m "not slow"
- name: Slow tests
id: server_integration_tests_slow
if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
run: |
cd tools/server/tests
SLOW_TESTS=1 pytest -v -x
- name: Tests (Backend sampling)
id: server_integration_tests_backend_sampling
run: |
cd tools/server/tests
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
- name: Slow tests (Backend sampling)
id: server_integration_tests_slow_backend_sampling
if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
run: |
cd tools/server/tests
export LLAMA_ARG_BACKEND_SAMPLING=1
SLOW_TESTS=1 pytest -v -x
windows:
runs-on: windows-2025
steps:
- name: Clone
id: checkout
uses: actions/checkout@v6
with:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: server-windows-2025-x64
evict-old-files: 1d
save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
- name: Build
id: cmake_build
shell: cmd
run: |
cmake -B build -G "Ninja Multi-Config" ^
-DCMAKE_TOOLCHAIN_FILE=cmake/x64-windows-llvm.cmake ^
-DCMAKE_BUILD_TYPE=Release ^
-DLLAMA_BUILD_BORINGSSL=ON ^
-DGGML_SCHED_NO_REALLOC=ON
set /A NINJA_JOBS=%NUMBER_OF_PROCESSORS%-1
cmake --build build --config Release -j %NINJA_JOBS% --target llama-server
- name: Python setup
id: setup_python
uses: actions/setup-python@v6
with:
python-version: '3.11'
pip-install: -r tools/server/tests/requirements.txt
- name: Tests
id: server_integration_tests
run: |
cd tools/server/tests
$env:PYTHONIOENCODING = ":replace"
pytest -v -x -m "not slow"
- name: Slow tests
id: server_integration_tests_slow
if: ${{ github.event.schedule || github.event.inputs.slow_tests == 'true' }}
run: |
cd tools/server/tests
$env:SLOW_TESTS = "1"
pytest -v -x