sleepy/llama.cpp
1
0
Fork 0
Code Issues 11 Pull Requests Actions 108 Packages Projects Releases Wiki Activity

docker : add CUDA 13.1 image build (#18441)

Browse Source 
* add updated cuda-new.Dockerfile for Ubuntu 24.04 compatibilty

* add cuda13 build
This commit is contained in:
Sigbjørn Skjæret
2025-12-30 22:28:53 +01:00
committed by GitHub
parent 6e0c8cbc40
commit 4849661d98
2 changed files with 119 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.github/workflows/docker.yml
+24 -11
View File
@@ -40,7 +40,8 @@ jobs:
# https://github.com/ggml-org/llama.cpp/issues/11888
#- { tag: "cpu", dockerfile: ".devops/cpu.Dockerfile", platforms: "linux/amd64,linux/arm64", full: true, light: true, server: true, free_disk_space: false }
- { tag: "cpu", dockerfile: ".devops/cpu.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: false, runs_on: "ubuntu-22.04" }
- { tag: "cuda", dockerfile: ".devops/cuda.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true, runs_on: "ubuntu-22.04" }
- { tag: "cuda cuda12", dockerfile: ".devops/cuda.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true, runs_on: "ubuntu-22.04", cuda_version: "12.4.0", ubuntu_version: "22.04" }
- { tag: "cuda13", dockerfile: ".devops/cuda-new.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true, runs_on: "ubuntu-22.04", cuda_version: "13.1.0", ubuntu_version: "24.04" }
- { tag: "musa", dockerfile: ".devops/musa.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true, runs_on: "ubuntu-22.04" }
- { tag: "intel", dockerfile: ".devops/intel.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: true, runs_on: "ubuntu-22.04" }
- { tag: "vulkan", dockerfile: ".devops/vulkan.Dockerfile", platforms: "linux/amd64", full: true, light: true, server: true, free_disk_space: false, runs_on: "ubuntu-22.04" }
@@ -80,18 +81,21 @@ jobs:
run: |
REPO_OWNER="${GITHUB_REPOSITORY_OWNER@L}" # to lower case
REPO_NAME="${{ github.event.repository.name }}"
PREFIX="ghcr.io/${REPO_OWNER}/${REPO_NAME}:"
# list all tags possible
if [[ "${{ matrix.config.tag }}" == "cpu" ]]; then
TYPE=""
else
TYPE="-${{ matrix.config.tag }}"
fi
PREFIX="ghcr.io/${REPO_OWNER}/${REPO_NAME}:"
CACHETAGS="${PREFIX}buildcache${TYPE}"
FULLTAGS="${PREFIX}full${TYPE},${PREFIX}full${TYPE}-${{ steps.srctag.outputs.name }}"
LIGHTTAGS="${PREFIX}light${TYPE},${PREFIX}light${TYPE}-${{ steps.srctag.outputs.name }}"
SERVERTAGS="${PREFIX}server${TYPE},${PREFIX}server${TYPE}-${{ steps.srctag.outputs.name }}"
tags="${{ matrix.config.tag }}"
for tag in $tags; do
if [[ "$tag" == "cpu" ]]; then
TYPE=""
else
TYPE="-$tag"
fi
CACHETAGS="${PREFIX}buildcache${TYPE}"
FULLTAGS="${FULLTAGS:+$FULLTAGS,}${PREFIX}full${TYPE},${PREFIX}full${TYPE}-${{ steps.srctag.outputs.name }}"
LIGHTTAGS="${LIGHTTAGS:+$LIGHTTAGS,}${PREFIX}light${TYPE},${PREFIX}light${TYPE}-${{ steps.srctag.outputs.name }}"
SERVERTAGS="${SERVERTAGS:+$SERVERTAGS,}${PREFIX}server${TYPE},${PREFIX}server${TYPE}-${{ steps.srctag.outputs.name }}"
done
echo "cache_output_tags=$CACHETAGS" >> $GITHUB_OUTPUT
echo "full_output_tags=$FULLTAGS" >> $GITHUB_OUTPUT
echo "light_output_tags=$LIGHTTAGS" >> $GITHUB_OUTPUT
@@ -132,6 +136,9 @@ jobs:
file: ${{ matrix.config.dockerfile }}
target: full
provenance: false
build-args: |
${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
# using github experimental cache
#cache-from: type=gha
#cache-to: type=gha,mode=max
@@ -154,6 +161,9 @@ jobs:
file: ${{ matrix.config.dockerfile }}
target: light
provenance: false
build-args: |
${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
# using github experimental cache
#cache-from: type=gha
#cache-to: type=gha,mode=max
@@ -176,6 +186,9 @@ jobs:
file: ${{ matrix.config.dockerfile }}
target: server
provenance: false
build-args: |
${{ matrix.config.ubuntu_version && format('UBUNTU_VERSION={0}', matrix.config.ubuntu_version) || '' }}
${{ matrix.config.cuda_version && format('CUDA_VERSION={0}', matrix.config.cuda_version) || '' }}
# using github experimental cache
#cache-from: type=gha
#cache-to: type=gha,mode=max