Files
LocalAI/pkg/startup/model_preload.go
Ettore Di Giacinto 2d64269763
Some checks failed
Explorer deployment / build-linux (push) Has been cancelled
GPU tests / ubuntu-latest (1.21.x) (push) Has been cancelled
generate and publish intel docker caches / generate_caches (intel/oneapi-basekit:2025.1.0-0-devel-ubuntu22.04, linux/amd64, ubuntu-latest) (push) Has been cancelled
build container images / hipblas-jobs (-aio-gpu-hipblas, rocm/dev-ubuntu-22.04:6.1, hipblas, true, ubuntu:22.04, core, latest-gpu-hipblas, latest-aio-gpu-hipblas, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -hipblas) (push) Has been cancelled
build container images / core-image-build (-aio-cpu, ubuntu:22.04, , true, core, latest-cpu, latest-aio-cpu, --jobs=4 --output-sync=target, linux/amd64,linux/arm64, arc-runner-set, false, auto, ) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-intel-f16, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, true, ubuntu:22.04, core, latest-gpu-intel-f16, latest-aio-gpu-intel-f16, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f16) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-intel-f32, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, true, ubuntu:22.04, core, latest-gpu-intel-f32, latest-aio-gpu-intel-f32, --jobs=3 --output-sync=target, linux/amd64, arc-runner-set, false, -sycl-f32) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-nvidia-cuda-11, ubuntu:22.04, cublas, 11, 7, true, core, latest-gpu-nvidia-cuda-11, latest-aio-gpu-nvidia-cuda-11, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda11) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-nvidia-cuda-12, ubuntu:22.04, cublas, 12, 0, true, core, latest-gpu-nvidia-cuda-12, latest-aio-gpu-nvidia-cuda-12, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -cublas-cuda12) (push) Has been cancelled
build container images / core-image-build (-aio-gpu-vulkan, ubuntu:22.04, vulkan, true, core, latest-gpu-vulkan, latest-aio-gpu-vulkan, --jobs=4 --output-sync=target, linux/amd64, arc-runner-set, false, false, -vulkan) (push) Has been cancelled
build container images / gh-runner (nvcr.io/nvidia/l4t-jetpack:r36.4.0, cublas, 12, 0, true, core, latest-nvidia-l4t-arm64, --jobs=4 --output-sync=target, linux/arm64, ubuntu-24.04-arm, true, false, -nvidia-l4t-arm64) (push) Has been cancelled
build python backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-bark, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-bark, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-bark, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-bark, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-bark) (push) Has been cancelled
build python backend container images / backend-jobs (bark, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-bark, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-bark) (push) Has been cancelled
build python backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-chatterbox, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-chatterbox) (push) Has been cancelled
build python backend container images / backend-jobs (chatterbox, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-chatterbox, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-chatterbox) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-coqui, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-coqui, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-coqui, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-coqui, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (coqui, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-coqui, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-coqui) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-diffusers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-diffusers, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-diffusers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (diffusers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-diffusers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-diffusers) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (faster-whisper, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-faster-whisper, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-faster-whisper) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-kokoro, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-kokoro, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-kokoro, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-kokoro, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (kokoro, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-kokoro, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-kokoro) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-rerankers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-rerankers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-rerankers, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-rerankers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (rerankers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-rerankers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-rerankers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-transformers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-transformers, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-transformers, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-transformers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (transformers, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-transformers, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-transformers) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f16, , , latest-gpu-intel-sycl-f16-vllm, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f16-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, quay.io/go-skynet/intel-oneapi-base:latest, sycl_f32, , , latest-gpu-intel-sycl-f32-vllm, linux/amd64, arc-runner-set, true, -gpu-intel-sycl-f32-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, rocm/dev-ubuntu-22.04:6.1, hipblas, , , latest-gpu-rocm-hipblas-vllm, linux/amd64, arc-runner-set, true, -gpu-rocm-hipblas-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, 11, 7, latest-gpu-nvidia-cuda-11-vllm, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-11-vllm) (push) Has been cancelled
build python backend container images / backend-jobs (vllm, ubuntu:22.04, cublas, 12, 0, latest-gpu-nvidia-cuda-12-vllm, linux/amd64, arc-runner-set, true, -gpu-nvidia-cuda-12-vllm) (push) Has been cancelled
Security Scan / tests (push) Has been cancelled
Tests extras backends / tests-transformers (push) Has been cancelled
Tests extras backends / tests-rerankers (push) Has been cancelled
Tests extras backends / tests-diffusers (push) Has been cancelled
Tests extras backends / tests-coqui (push) Has been cancelled
tests / tests-linux (1.21.x) (push) Has been cancelled
tests / tests-aio-container (push) Has been cancelled
tests / tests-apple (1.21.x) (push) Has been cancelled
Update swagger / swagger (push) Has been cancelled
Check if checksums are up-to-date / checksum_check (push) Has been cancelled
Bump dependencies / bump (mudler/LocalAI) (push) Has been cancelled
Bump dependencies / bump (main, PABannier/bark.cpp, BARKCPP_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, ggml-org/llama.cpp, CPPLLAMA_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, ggml-org/whisper.cpp, WHISPER_CPP_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, leejet/stable-diffusion.cpp, STABLEDIFFUSION_GGML_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, mudler/go-piper, PIPER_VERSION) (push) Has been cancelled
Bump dependencies / bump (master, mudler/go-stable-diffusion, STABLEDIFFUSION_VERSION) (push) Has been cancelled
feat: Add backend gallery (#5607)
* feat: Add backend gallery

This PR add support to manage backends as similar to models. There is
now available a backend gallery which can be used to install and remove
extra backends.
The backend gallery can be configured similarly as a model gallery, and
API calls allows to install and remove new backends in runtime, and as
well during the startup phase of LocalAI.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add backends docs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* wip: Backend Dockerfile for python backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat: drop extras images, build python backends separately

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixup on all backends

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Tweaks

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Drop old backends leftovers

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixup CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Move dockerfile upper

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fix proto

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Feature dropped for consistency - we prefer model galleries

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add missing packages in the build image

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* exllama is ponly available on cublas

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* pin torch on chatterbox

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Fixups to index

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Debug CI

* Install accellerators deps

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Add target arch

* Add cuda minor version

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Use self-hosted runners

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* ci: use quay for test images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fixups for vllm and chatterbox

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Small fixups on CI

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chatterbox is only available for nvidia

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Simplify CI builds

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Adapt test, use qwen3

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* chore(model gallery): add jina-reranker-v1-tiny-en-gguf

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(gguf-parser): recover from potential panics that can happen while reading ggufs with gguf-parser

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Use reranker from llama.cpp in AIO images

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* Limit concurrent jobs

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
2025-06-15 14:56:52 +02:00

139 lines
4.7 KiB
Go

package startup
import (
"errors"
"fmt"
"os"
"path/filepath"
"strings"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/gallery"
"github.com/mudler/LocalAI/pkg/downloader"
"github.com/mudler/LocalAI/pkg/utils"
"github.com/rs/zerolog/log"
)
// InstallModels will preload models from the given list of URLs and galleries
// It will download the model if it is not already present in the model path
// It will also try to resolve if the model is an embedded model YAML configuration
func InstallModels(galleries []config.Gallery, modelPath string, enforceScan bool, downloadStatus func(string, string, string, float64), models ...string) error {
// create an error that groups all errors
var err error
for _, url := range models {
// As a best effort, try to resolve the model from the remote library
// if it's not resolved we try with the other method below
uri := downloader.URI(url)
switch {
case uri.LooksLikeOCI():
log.Debug().Msgf("[startup] resolved OCI model to download: %s", url)
// convert OCI image name to a file name.
ociName := strings.TrimPrefix(url, downloader.OCIPrefix)
ociName = strings.TrimPrefix(ociName, downloader.OllamaPrefix)
ociName = strings.ReplaceAll(ociName, "/", "__")
ociName = strings.ReplaceAll(ociName, ":", "__")
// check if file exists
if _, e := os.Stat(filepath.Join(modelPath, ociName)); errors.Is(e, os.ErrNotExist) {
modelDefinitionFilePath := filepath.Join(modelPath, ociName)
e := uri.DownloadFile(modelDefinitionFilePath, "", 0, 0, func(fileName, current, total string, percent float64) {
utils.DisplayDownloadFunction(fileName, current, total, percent)
})
if e != nil {
log.Error().Err(e).Str("url", url).Str("filepath", modelDefinitionFilePath).Msg("error downloading model")
err = errors.Join(err, e)
}
}
log.Info().Msgf("[startup] installed model from OCI repository: %s", ociName)
case uri.LooksLikeURL():
log.Debug().Msgf("[startup] downloading %s", url)
// Extract filename from URL
fileName, e := uri.FilenameFromUrl()
if e != nil {
log.Warn().Err(e).Str("url", url).Msg("error extracting filename from URL")
err = errors.Join(err, e)
continue
}
modelPath := filepath.Join(modelPath, fileName)
if e := utils.VerifyPath(fileName, modelPath); e != nil {
log.Error().Err(e).Str("filepath", modelPath).Msg("error verifying path")
err = errors.Join(err, e)
continue
}
// check if file exists
if _, e := os.Stat(modelPath); errors.Is(e, os.ErrNotExist) {
e := uri.DownloadFile(modelPath, "", 0, 0, func(fileName, current, total string, percent float64) {
utils.DisplayDownloadFunction(fileName, current, total, percent)
})
if e != nil {
log.Error().Err(e).Str("url", url).Str("filepath", modelPath).Msg("error downloading model")
err = errors.Join(err, e)
}
}
default:
if _, e := os.Stat(url); e == nil {
log.Debug().Msgf("[startup] resolved local model: %s", url)
// copy to modelPath
md5Name := utils.MD5(url)
modelYAML, e := os.ReadFile(url)
if e != nil {
log.Error().Err(e).Str("filepath", url).Msg("error reading model definition")
err = errors.Join(err, e)
continue
}
modelDefinitionFilePath := filepath.Join(modelPath, md5Name) + ".yaml"
if e := os.WriteFile(modelDefinitionFilePath, modelYAML, 0600); e != nil {
log.Error().Err(err).Str("filepath", modelDefinitionFilePath).Msg("error loading model: %s")
err = errors.Join(err, e)
}
} else {
// Check if it's a model gallery, or print a warning
e, found := installModel(galleries, url, modelPath, downloadStatus, enforceScan)
if e != nil && found {
log.Error().Err(err).Msgf("[startup] failed installing model '%s'", url)
err = errors.Join(err, e)
} else if !found {
log.Warn().Msgf("[startup] failed resolving model '%s'", url)
err = errors.Join(err, fmt.Errorf("failed resolving model '%s'", url))
}
}
}
}
return err
}
func installModel(galleries []config.Gallery, modelName, modelPath string, downloadStatus func(string, string, string, float64), enforceScan bool) (error, bool) {
models, err := gallery.AvailableGalleryModels(galleries, modelPath)
if err != nil {
return err, false
}
model := gallery.FindGalleryElement(models, modelName, modelPath)
if model == nil {
return err, false
}
if downloadStatus == nil {
downloadStatus = utils.DisplayDownloadFunction
}
log.Info().Str("model", modelName).Str("license", model.License).Msg("installing model")
err = gallery.InstallModelFromGallery(galleries, modelName, modelPath, gallery.GalleryModel{}, downloadStatus, enforceScan)
if err != nil {
return err, true
}
return nil, true
}