mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-11-01 07:30:17 +01:00
1c641e6aac
* `main`/`server`: rename to `llama` / `llama-server` for consistency w/ homebrew
* server: update refs -> llama-server
gitignore llama-server
* server: simplify nix package
* main: update refs -> llama
fix examples/main ref
* main/server: fix targets
* update more names
* Update build.yml
* rm accidentally checked in bins
* update straggling refs
* Update .gitignore
* Update server-llm.sh
* main: target name -> llama-cli
* Prefix all example bins w/ llama-
* fix main refs
* rename {main->llama}-cmake-pkg binary
* prefix more cmake targets w/ llama-
* add/fix gbnf-validator subfolder to cmake
* sort cmake example subdirs
* rm bin files
* fix llama-lookup-* Makefile rules
* gitignore /llama-*
* rename Dockerfiles
* rename llama|main -> llama-cli; consistent RPM bin prefixes
* fix some missing -cli suffixes
* rename dockerfile w/ llama-cli
* rename(make): llama-baby-llama
* update dockerfile refs
* more llama-cli(.exe)
* fix test-eval-callback
* rename: llama-cli-cmake-pkg(.exe)
* address gbnf-validator unused fread warning (switched to C++ / ifstream)
* add two missing llama- prefixes
* Updating docs for eval-callback binary to use new `llama-` prefix.
* Updating a few lingering doc references for rename of main to llama-cli
* Updating `run-with-preset.py` to use new binary names.
Updating docs around `perplexity` binary rename.
* Updating documentation references for lookup-merge and export-lora
* Updating two small `main` references missed earlier in the finetune docs.
* Update apps.nix
* update grammar/README.md w/ new llama-* names
* update llama-rpc-server bin name + doc
* Revert "update llama-rpc-server bin name + doc"
This reverts commit e474ef1df4
.
* add hot topic notice to README.md
* Update README.md
* Update README.md
* rename gguf-split & quantize bins refs in **/tests.sh
---------
Co-authored-by: HanClinto <hanclinto@gmail.com>
118 lines
4.9 KiB
YAML
118 lines
4.9 KiB
YAML
# This workflow uses actions that are not certified by GitHub.
|
|
# They are provided by a third-party and are governed by
|
|
# separate terms of service, privacy policy, and support
|
|
# documentation.
|
|
|
|
# GitHub recommends pinning actions to a commit SHA.
|
|
# To get a newer version, you will need to update the SHA.
|
|
# You can also reference a tag or branch, but the action may change without warning.
|
|
|
|
name: Publish Docker image
|
|
|
|
on:
|
|
pull_request:
|
|
push:
|
|
branches:
|
|
- master
|
|
|
|
concurrency:
|
|
group: ${{ github.workflow }}-${{ github.head_ref && github.ref || github.run_id }}
|
|
cancel-in-progress: true
|
|
|
|
jobs:
|
|
push_to_registry:
|
|
name: Push Docker image to Docker Hub
|
|
if: github.event.pull_request.draft == false
|
|
|
|
runs-on: ubuntu-latest
|
|
env:
|
|
COMMIT_SHA: ${{ github.sha }}
|
|
strategy:
|
|
matrix:
|
|
config:
|
|
- { tag: "light", dockerfile: ".devops/llama-cli.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
|
- { tag: "server", dockerfile: ".devops/llama-server.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
|
- { tag: "full", dockerfile: ".devops/full.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
|
# NOTE(canardletter): The CUDA builds on arm64 are very slow, so I
|
|
# have disabled them for now until the reason why
|
|
# is understood.
|
|
- { tag: "light-cuda", dockerfile: ".devops/llama-cli-cuda.Dockerfile", platforms: "linux/amd64" }
|
|
- { tag: "server-cuda", dockerfile: ".devops/llama-server-cuda.Dockerfile", platforms: "linux/amd64" }
|
|
- { tag: "full-cuda", dockerfile: ".devops/full-cuda.Dockerfile", platforms: "linux/amd64" }
|
|
- { tag: "light-rocm", dockerfile: ".devops/llama-cli-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
|
- { tag: "server-rocm", dockerfile: ".devops/llama-server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
|
- { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
|
|
- { tag: "light-intel", dockerfile: ".devops/llama-cli-intel.Dockerfile", platforms: "linux/amd64" }
|
|
- { tag: "server-intel", dockerfile: ".devops/llama-server-intel.Dockerfile", platforms: "linux/amd64" }
|
|
steps:
|
|
- name: Check out the repo
|
|
uses: actions/checkout@v4
|
|
|
|
- name: Set up QEMU
|
|
uses: docker/setup-qemu-action@v2
|
|
|
|
- name: Set up Docker Buildx
|
|
uses: docker/setup-buildx-action@v2
|
|
|
|
- name: Log in to Docker Hub
|
|
uses: docker/login-action@v2
|
|
with:
|
|
registry: ghcr.io
|
|
username: ${{ github.repository_owner }}
|
|
password: ${{ secrets.GITHUB_TOKEN }}
|
|
|
|
# https://github.com/jlumbroso/free-disk-space/tree/54081f138730dfa15788a46383842cd2f914a1be#example
|
|
- name: Free Disk Space (Ubuntu)
|
|
uses: jlumbroso/free-disk-space@main
|
|
with:
|
|
# this might remove tools that are actually needed,
|
|
# if set to "true" but frees about 6 GB
|
|
tool-cache: false
|
|
|
|
# all of these default to true, but feel free to set to
|
|
# "false" if necessary for your workflow
|
|
android: true
|
|
dotnet: true
|
|
haskell: true
|
|
large-packages: true
|
|
docker-images: true
|
|
swap-storage: true
|
|
|
|
- name: Determine tag name
|
|
id: tag
|
|
shell: bash
|
|
run: |
|
|
BUILD_NUMBER="$(git rev-list --count HEAD)"
|
|
SHORT_HASH="$(git rev-parse --short=7 HEAD)"
|
|
if [[ "${{ env.BRANCH_NAME }}" == "master" ]]; then
|
|
echo "name=b${BUILD_NUMBER}" >> $GITHUB_OUTPUT
|
|
else
|
|
SAFE_NAME=$(echo "${{ env.BRANCH_NAME }}" | tr '/' '-')
|
|
echo "name=${SAFE_NAME}-b${BUILD_NUMBER}-${SHORT_HASH}" >> $GITHUB_OUTPUT
|
|
fi
|
|
|
|
- name: Downcase github.repository_owner
|
|
run: |
|
|
echo "repository_owner_lowercase=${GITHUB_REPOSITORY_OWNER@L}" >> $GITHUB_ENV
|
|
env:
|
|
GITHUB_REPOSITORY_OWNER: '${{ github.repository_owner }}'
|
|
|
|
- name: Build and push Docker image (versioned)
|
|
if: github.event_name == 'push'
|
|
uses: docker/build-push-action@v4
|
|
with:
|
|
context: .
|
|
push: true
|
|
platforms: ${{ matrix.config.platforms }}
|
|
tags: "ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }}-${{ env.COMMIT_SHA }}"
|
|
file: ${{ matrix.config.dockerfile }}
|
|
|
|
- name: Build and push Docker image (tagged)
|
|
uses: docker/build-push-action@v4
|
|
with:
|
|
context: .
|
|
push: ${{ github.event_name == 'push' }}
|
|
platforms: ${{ matrix.config.platforms }}
|
|
tags: "ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }},ghcr.io/${{ env.repository_owner_lowercase }}/llama.cpp:${{ matrix.config.tag }}-${{ steps.tag.outputs.name }}"
|
|
file: ${{ matrix.config.dockerfile }}
|