nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 4 Packages Projects Releases Wiki Activity

ci : refactor (#23789)

Browse Source 
* ci : separate CUDA windows workflow + fix names

* ci : rename workflow

* ci : prefix cache names with workflow name

* ci : rename build.yml -> build-cpu.yml

* ci : cache keys

* ci : fix windows cuda/hip concurrency of release workflow

* ci : fix apple cache names

* ci : add TODOs

* cont : keep just the last cache

* ci : update release concurrency to queue

* ci : move the release trigger to ubuntu-slim

* ci : hip add TODO

* cont : improve words

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Georgi Gerganov
2026-05-28 09:44:25 +03:00
committed by GitHub
parent 939a7dd648
commit 491c4d7d2e
18 changed files with 342 additions and 303 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
.github/workflows/release.yml vendored
View File

@@ -27,18 +27,18 @@ on:
'**/*.glsl'
]
concurrency:
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
cancel-in-progress: true
env:
BRANCH_NAME: ${{ github.head_ref || github.ref_name }}
CMAKE_ARGS: "-DLLAMA_BUILD_EXAMPLES=OFF -DLLAMA_BUILD_TESTS=OFF -DLLAMA_BUILD_TOOLS=ON -DLLAMA_BUILD_SERVER=ON -DGGML_RPC=ON"
jobs:
# note: run this workflow one at a time for better cache reuse
concurrency:
group: release
queue: max
jobs:
check_release:
runs-on: [self-hosted, fast]
runs-on: ubuntu-slim
outputs:
should_release: ${{ steps.check.outputs.should_release }}
@@ -100,8 +100,8 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: macos-latest-${{ matrix.arch }}
evict-old-files: 1d
key: release-${{ matrix.os }}-${{ matrix.arch }}
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Build
id: cmake_build
@@ -165,8 +165,8 @@ jobs:
if: ${{ matrix.build != 's390x' }}
uses: ggml-org/ccache-action@v1.2.21
with:
key: ubuntu-cpu-${{ matrix.build }}
evict-old-files: 1d
key: release-${{ matrix.os }}-cpu
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Dependencies
id: depends
@@ -241,8 +241,8 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: ubuntu-vulkan-${{ matrix.build }}
evict-old-files: 1d
key: release-${{ matrix.os }}-vulkan
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Dependencies
id: depends
@@ -311,11 +311,17 @@ jobs:
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: android-arm64
evict-old-files: 1d
# note : disabled to spare some cache space (https://github.com/ggml-org/llama.cpp/pull/23789)
# for some reason, the ccache does not improve the build time in this case
# example:
# cache off: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78160400831
# cache on: https://github.com/ggerganov/tmp2/actions/runs/26534713799/job/78224189394
#
#- name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: release-android-arm64
# append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Set up JDK
uses: actions/setup-java@v5
@@ -402,8 +408,8 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: ubuntu-24-openvino-release-no-preset-v1
evict-old-files: 1d
key: release-ubuntu-24.04-openvino-release-no-preset-v1
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Dependencies
run: |
@@ -485,9 +491,8 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: windows-latest-cpu-${{ matrix.arch }}
variant: ccache
evict-old-files: 1d
key: release-windows-2025-${{ matrix.arch }}-cpu
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Install Ninja
run: |
@@ -556,9 +561,8 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: windows-latest-${{ matrix.backend }}-${{ matrix.arch }}
variant: ccache
evict-old-files: 1d
key: release-windows-2025-${{ matrix.arch }}-${{ matrix.backend }}
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Install Vulkan SDK
id: get_vulkan
@@ -633,12 +637,11 @@ jobs:
cache: "npm"
cache-dependency-path: "tools/ui/package-lock.json"
- name: Install ccache
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: windows-cuda-${{ matrix.cuda }}
variant: ccache
evict-old-files: 1d
key: release-windows-2022-x64-cuda-${{ matrix.cuda }}
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Install Cuda Toolkit
uses: ./.github/actions/windows-setup-cuda
@@ -744,9 +747,8 @@ jobs:
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: windows-latest-sycl
# variant: ccache
# evict-old-files: 1d
# key: release-windows-2022-x64-sycl
# append-timestamp: false # note: use this only with non-concurrent jobs!
#
# - name: Build
# id: cmake_build
@@ -866,9 +868,8 @@ jobs:
# - name: ccache
# uses: ggml-org/ccache-action@v1.2.21
# with:
# key: ubuntu-24-sycl-${{ matrix.build }}
# evict-old-files: 1d
# save: ${{ github.event_name == 'push' && github.ref == 'refs/heads/master' }}
# key: release-ubuntu-24.04-sycl
# append-timestamp: false # note: use this only with non-concurrent jobs!
#
# - name: Build
# id: cmake_build
@@ -936,8 +937,8 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: ubuntu-rocm-${{ matrix.ROCM_VERSION }}-${{ matrix.build }}
evict-old-files: 1d
key: release-ubuntu-22.04-rocm-${{ matrix.ROCM_VERSION }}
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Dependencies
id: depends
@@ -1058,8 +1059,8 @@ jobs:
- name: ccache
uses: ggml-org/ccache-action@v1.2.21
with:
key: windows-latest-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}-x64
evict-old-files: 1d
key: release-windows-2022-x64-hip-${{ env.HIPSDK_INSTALLER_VERSION }}-${{ matrix.name }}
append-timestamp: false # note: use this only with non-concurrent jobs!
- name: Install ROCm
if: steps.cache-rocm.outputs.cache-hit != 'true'