vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

docker : add server-first container images (#5157)

Browse source 
* feat: add Dockerfiles for each platform that user ./server instead of ./main

* feat: update .github/workflows/docker.yml to build server-first docker containers

* doc: add information about running the server with Docker to README.md

* doc: add information about running with docker to the server README

* doc: update n-gpu-layers to show correct GPU usage

* fix(doc): update container tag from `server` to `server-cuda` for README example on running server container with CUDA
This commit is contained in:
Kyle Mistele 2024-01-28 01:55:31 -06:00 • committed by GitHub
parent 6db2b41a76
commit 39baaf55a1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 147 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

4
.github/workflows/docker.yml vendored
View file

@ -28,14 +28,18 @@ jobs:
config:
- { tag: "light", dockerfile: ".devops/main.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- { tag: "full", dockerfile: ".devops/full.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- { tag: "server", dockerfile: ".devops/server.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/main-cuda.Dockerfile", platforms: "linux/amd64" }
- { tag: "full-cuda", dockerfile: ".devops/full-cuda.Dockerfile", platforms: "linux/amd64" }
- { tag: "server-cuda", dockerfile: ".devops/server-cuda.Dockerfile", platforms: "linux/amd64" }
- { tag: "light-rocm", dockerfile: ".devops/main-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- { tag: "full-rocm", dockerfile: ".devops/full-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- { tag: "server-rocm", dockerfile: ".devops/server-rocm.Dockerfile", platforms: "linux/amd64,linux/arm64" }
- { tag: "light-intel", dockerfile: ".devops/main-intel.Dockerfile", platforms: "linux/amd64" }
- { tag: "server-intel", dockerfile: ".devops/server-intel.Dockerfile", platforms: "linux/amd64" }
steps:
- name: Check out the repo
uses: actions/checkout@v3