mirror of
https://github.com/mudler/LocalAI.git
synced 2026-06-12 02:38:19 -04:00
feat(dllm): backend packaging, gallery index, CI matrix
Registers the dllm backend across every surface: backend gallery index (cpu amd64+arm64 with manifest merge, cuda13, l4t-cuda13 for GB10-class hardware; no darwin per engine scope), top-level Makefile targets, bump_deps pin tracking for DLLM_VERSION, and the curated known-backends list for /backends/known (pref-only: auto-detecting on .gguf would shadow llama-cpp). Note: image builds and the nightly bump leg stay red until github.com/mudler/dllm.cpp is published (planned at merge time). Assisted-by: Claude Code (Fable 5) Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
This commit is contained in:
55
.github/backend-matrix.yml
vendored
55
.github/backend-matrix.yml
vendored
@@ -1608,6 +1608,19 @@ include:
|
||||
dockerfile: "./backend/Dockerfile.golang"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "13"
|
||||
cuda-minor-version: "0"
|
||||
platforms: 'linux/amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-gpu-nvidia-cuda-13-dllm'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "dllm"
|
||||
dockerfile: "./backend/Dockerfile.golang"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "13"
|
||||
cuda-minor-version: "0"
|
||||
@@ -1647,6 +1660,19 @@ include:
|
||||
backend: "parakeet-cpp"
|
||||
dockerfile: "./backend/Dockerfile.golang"
|
||||
context: "./"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "13"
|
||||
cuda-minor-version: "0"
|
||||
platforms: 'linux/arm64'
|
||||
skip-drivers: 'false'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-nvidia-l4t-cuda-13-arm64-dllm'
|
||||
base-image: "ubuntu:24.04"
|
||||
ubuntu-version: '2404'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
backend: "dllm"
|
||||
dockerfile: "./backend/Dockerfile.golang"
|
||||
context: "./"
|
||||
- build-type: 'cublas'
|
||||
cuda-major-version: "13"
|
||||
cuda-minor-version: "0"
|
||||
@@ -3145,6 +3171,35 @@ include:
|
||||
dockerfile: "./backend/Dockerfile.golang"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
# dllm
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/amd64'
|
||||
platform-tag: 'amd64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-dllm'
|
||||
runs-on: 'ubuntu-latest'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "dllm"
|
||||
dockerfile: "./backend/Dockerfile.golang"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: ''
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
platforms: 'linux/arm64'
|
||||
platform-tag: 'arm64'
|
||||
tag-latest: 'auto'
|
||||
tag-suffix: '-cpu-dllm'
|
||||
runs-on: 'ubuntu-24.04-arm'
|
||||
base-image: "ubuntu:24.04"
|
||||
skip-drivers: 'false'
|
||||
backend: "dllm"
|
||||
dockerfile: "./backend/Dockerfile.golang"
|
||||
context: "./"
|
||||
ubuntu-version: '2404'
|
||||
- build-type: 'sycl_f32'
|
||||
cuda-major-version: ""
|
||||
cuda-minor-version: ""
|
||||
|
||||
4
.github/workflows/bump_deps.yaml
vendored
4
.github/workflows/bump_deps.yaml
vendored
@@ -38,6 +38,10 @@ jobs:
|
||||
variable: "PARAKEET_VERSION"
|
||||
branch: "master"
|
||||
file: "backend/go/parakeet-cpp/Makefile"
|
||||
- repository: "mudler/dllm.cpp"
|
||||
variable: "DLLM_VERSION"
|
||||
branch: "main"
|
||||
file: "backend/go/dllm/Makefile"
|
||||
- repository: "leejet/stable-diffusion.cpp"
|
||||
variable: "STABLEDIFFUSION_GGML_VERSION"
|
||||
branch: "master"
|
||||
|
||||
Reference in New Issue
Block a user