jdelony/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-06-27 23:50:20 -05:00
Code Issues Packages Projects Releases Wiki Activity

ci : reduce self-hosted server workflow jobs (#24012)

Browse Source 
Reduce the number of parallel jobs in server-self-hosted.yml by stacking
test configurations as sequential steps within a single job, following the
pattern from #23927.

- server-metal: 4 matrix jobs -> 1 job with 4 sequential test steps
- server-cuda: 2 matrix jobs -> 1 job with 2 sequential test steps
- server-kleidiai: removed unnecessary single-entry matrix
- removed unused Setup Node.js step from server-metal

Total: 7 parallel jobs -> 3 parallel jobs

Assisted-by: llama.cpp:local pi
This commit is contained in:
Georgi Gerganov 2026-06-02 13:17:59 +03:00 committed by GitHub
parent d5ab0834ab
commit a468b89018
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 67 additions and 61 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

128
.github/workflows/server-self-hosted.yml vendored
View File

@ -42,23 +42,6 @@ jobs:
server-metal:
runs-on: [self-hosted, llama-server, macOS, ARM64]
name: server-metal (${{ matrix.wf_name }})
strategy:
matrix:
build_type: [Release]
wf_name: ["GPUx1"]
include:
- build_type: Release
extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
wf_name: "GPUx1, backend-sampling"
- build_type: Release
extra_args: "GGML_METAL_DEVICES=2"
wf_name: "GPUx2"
- build_type: Release
extra_args: "GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1"
wf_name: "GPUx2, backend-sampling"
fail-fast: false
steps:
- name: Clone
id: checkout
@ -67,44 +50,58 @@ jobs:
fetch-depth: 0
ref: ${{ github.event.inputs.sha || github.event.pull_request.head.sha || github.sha || github.head_ref || github.ref_name }}
- name: Setup Node.js
uses: actions/setup-node@v6
with:
node-version: "24"
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Build
id: cmake_build
run: |
cmake -B build -DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config ${{ matrix.build_type }} -j $(sysctl -n hw.logicalcpu) --target llama-server
cmake --build build --config Release -j $(sysctl -n hw.logicalcpu) --target llama-server
- name: Tests
id: server_integration_tests
if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
- name: Python setup
id: setup_python
run: |
cd tools/server/tests
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
export ${{ matrix.extra_args }}
- name: Tests (GPUx1)
id: server_integration_tests
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
- name: Tests (GPUx2)
id: server_integration_tests_gpu2
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2
pytest -v -x -m "not slow"
- name: Tests (GPUx2, backend-sampling)
id: server_integration_tests_gpu2_backend_sampling
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export GGML_METAL_DEVICES=2 LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
server-cuda:
runs-on: [self-hosted, llama-server, Linux, NVIDIA]
name: server-cuda (${{ matrix.wf_name }})
strategy:
matrix:
build_type: [Release]
wf_name: ["GPUx1"]
include:
- build_type: Release
extra_args: "LLAMA_ARG_BACKEND_SAMPLING=1"
wf_name: "GPUx1, backend-sampling"
fail-fast: false
steps:
- name: Clone
id: checkout
@ -117,32 +114,36 @@ jobs:
id: cmake_build
run: |
cmake -B build -DGGML_CUDA=ON -DGGML_SCHED_NO_REALLOC=ON
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Tests
id: server_integration_tests
if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
- name: Python setup
id: setup_python
run: |
cd tools/server/tests
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
export ${{ matrix.extra_args }}
- name: Tests (GPUx1)
id: server_integration_tests
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"
- name: Tests (GPUx1, backend-sampling)
id: server_integration_tests_backend_sampling
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
export LLAMA_ARG_BACKEND_SAMPLING=1
pytest -v -x -m "not slow"
server-kleidiai:
runs-on: ah-ubuntu_22_04-c8g_8x
name: server-kleidiai (${{ matrix.wf_name }})
strategy:
matrix:
include:
- build_type: Release
extra_build_flags: "-DGGML_CPU_KLEIDIAI=ON"
extra_args: ""
wf_name: "CPUx1, kleidiai"
fail-fast: false
steps:
- name: Clone
id: checkout
@ -181,16 +182,21 @@ jobs:
- name: Build
id: cmake_build
run: |
cmake -B build -DGGML_SCHED_NO_REALLOC=ON ${{ matrix.extra_build_flags }}
cmake --build build --config ${{ matrix.build_type }} -j $(nproc) --target llama-server
cmake -B build -DGGML_SCHED_NO_REALLOC=ON -DGGML_CPU_KLEIDIAI=ON
cmake --build build --config Release -j $(nproc) --target llama-server
- name: Tests
id: server_integration_tests
if: ${{ (!matrix.disabled_on_pr || !github.event.pull_request) }}
- name: Python setup
id: setup_python
run: |
cd tools/server/tests
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
export ${{ matrix.extra_args }}
- name: Tests
id: server_integration_tests
if: ${{ !github.event.pull_request }}
run: |
cd tools/server/tests
source venv/bin/activate
pytest -v -x -m "not slow"