This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.6.1` -> `v2.7.0` | --- > [!WARNING] > Some dependencies could not be looked up. Check the Dependency Dashboard for more information. --- ### Release Notes <details> <summary>mudler/LocalAI (docker.io/localai/localai)</summary> ### [`v2.7.0`](https://togithub.com/mudler/LocalAI/releases/tag/v2.7.0) [Compare Source](https://togithub.com/mudler/LocalAI/compare/v2.6.1...v2.7.0) <!-- Release notes generated using configuration in .github/release.yml at master --> This release adds support to the transformer backend for LLM as well! For now instance you can run codellama-7b with transformers with: docker run -ti -p 8080:8080 --gpus all localai/localai:v2.7.0-cublas-cuda12 codellama-7b In the quickstart there are more examples available https://localai.io/basics/getting_started/#running-models. Note: As llama.cpp is ongoing with changes that could possible cause breakage, this release does not includes changes from [https://github.com/ggerganov/llama.cpp/discussions/5138](https://togithub.com/ggerganov/llama.cpp/discussions/5138) (the future versions will). #### What's Changed ##### Bug fixes 🐛 - fix(paths): automatically create paths by [@​mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1650](https://togithub.com/mudler/LocalAI/pull/1650) ##### Exciting New Features 🎉 - feat(transformers): support also text generation by [@​mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1630](https://togithub.com/mudler/LocalAI/pull/1630) - transformers: correctly load automodels by [@​mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1643](https://togithub.com/mudler/LocalAI/pull/1643) - feat(startup): fetch model definition remotely by [@​mudler](https://togithub.com/mudler) in [https://github.com/mudler/LocalAI/pull/1654](https://togithub.com/mudler/LocalAI/pull/1654) ##### 👒 Dependencies - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1642](https://togithub.com/mudler/LocalAI/pull/1642) - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1644](https://togithub.com/mudler/LocalAI/pull/1644) - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1652](https://togithub.com/mudler/LocalAI/pull/1652) - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1655](https://togithub.com/mudler/LocalAI/pull/1655) ##### Other Changes - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1632](https://togithub.com/mudler/LocalAI/pull/1632) - ⬆️ Update docs version mudler/LocalAI by [@​localai-bot](https://togithub.com/localai-bot) in [https://github.com/mudler/LocalAI/pull/1631](https://togithub.com/mudler/LocalAI/pull/1631) **Full Changelog**: https://github.com/mudler/LocalAI/compare/v2.6.1...v2.6.2 </details> --- ### Configuration 📅 **Schedule**: Branch creation - "before 10pm on monday" in timezone Europe/Amsterdam, Automerge - At any time (no schedule defined). 🚦 **Automerge**: Enabled. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about this update again. --- - [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://togithub.com/renovatebot/renovate). <!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiIzNy4xNTYuNCIsInVwZGF0ZWRJblZlciI6IjM3LjE1Ni40IiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIn0=-->
90 lines
2.8 KiB
YAML
90 lines
2.8 KiB
YAML
image:
|
|
repository: docker.io/localai/localai
|
|
pullPolicy: IfNotPresent
|
|
tag: v2.7.0@sha256:b689c9167204942b6ffd8ad7ee3362ab7f8fa9e852e0a084f83dbc946c03a301
|
|
ffmpegImage:
|
|
repository: docker.io/localai/localai
|
|
pullPolicy: IfNotPresent
|
|
tag: v2.7.0-ffmpeg-core@sha256:b5815fd4fdbe56f3d524b58155303995344da3fd417f7160b956cd7e9168fe4c
|
|
cublasCuda12Image:
|
|
repository: docker.io/localai/localai
|
|
pullPolicy: IfNotPresent
|
|
tag: v2.7.0-cublas-cuda12-core@sha256:1b4a32a63cc4118b9378569541d276cc880bf230b3d1da8d5f2cf43ec33cf1a3
|
|
cublasCuda12FfmpegImage:
|
|
repository: docker.io/localai/localai
|
|
pullPolicy: IfNotPresent
|
|
tag: v2.7.0-cublas-cuda12-ffmpeg-core@sha256:bf11fe260047002cd9206fec370ca1e78f360d68b5e386192f1c1a0bdee975c7
|
|
cublasCuda11Image:
|
|
repository: docker.io/localai/localai
|
|
pullPolicy: IfNotPresent
|
|
tag: v2.7.0-cublas-cuda11-core@sha256:7272a60b4dd96259d36f2ac346b97342c781d91d6e1924ade735b9b562a1d164
|
|
cublasCuda11FfmpegImage:
|
|
repository: docker.io/localai/localai
|
|
pullPolicy: IfNotPresent
|
|
tag: v2.7.0-cublas-cuda11-ffmpeg-core@sha256:e0e35edc309c9e83cacc122cc6e4af5aa95fbc7d7834312c47ce301220e6ef81
|
|
securityContext:
|
|
container:
|
|
runAsNonRoot: false
|
|
readOnlyRootFilesystem: false
|
|
runAsUser: 0
|
|
runAsGroup: 0
|
|
service:
|
|
main:
|
|
ports:
|
|
main:
|
|
protocol: http
|
|
port: 8080
|
|
localai:
|
|
# Specify a build type. Available: cublas, openblas, clblas.
|
|
build_type: "openblas"
|
|
debug: false
|
|
cors: true
|
|
cors_allow_origins: "*"
|
|
galleries: []
|
|
# - name: model-gallery
|
|
# url: github:go-skynet/model-gallery/index.yaml
|
|
preload_models: []
|
|
# url: github:go-skynet/model-gallery/gpt4all-j.yaml
|
|
# UPLOAD_LIMIT
|
|
workload:
|
|
main:
|
|
podSpec:
|
|
containers:
|
|
main:
|
|
probes:
|
|
liveness:
|
|
enabled: true
|
|
type: http
|
|
path: /readyz
|
|
readiness:
|
|
enabled: true
|
|
type: http
|
|
path: /readyz
|
|
startup:
|
|
enabled: true
|
|
type: tcp
|
|
imageSelector: image
|
|
env:
|
|
ADDRESS: ":{{ .Values.service.main.ports.main.port }}"
|
|
MODELS_PATH: "{{ .Values.persistence.models.mountPath }}"
|
|
IMAGE_PATH: "{{ .Values.persistence.images.mountPath }}"
|
|
BUILD_TYPE: "{{ .Values.localai.build_type }}"
|
|
# breaks chart if true, keep it false.
|
|
REBUILD: false
|
|
DEBUG: "{{ .Values.localai.debug }}"
|
|
CORS: "{{ .Values.localai.cors }}"
|
|
GALLERIES: "{{ toJson .Values.localai.galleries }}"
|
|
PRELOAD_MODELS: "{{ toJson .Values.localai.preload_models }}"
|
|
CORS_ALLOW_ORIGINS: "{{ .Values.localai.cors_allow_origins }}"
|
|
persistence:
|
|
models:
|
|
enabled: true
|
|
mountPath: "/models"
|
|
images:
|
|
enabled: true
|
|
mountPath: "/images"
|
|
portal:
|
|
open:
|
|
enabled: false
|
|
updated: true
|