Deprecation of old backends #1651
Labels
enhancement
New feature or request
Comments
This was referenced Feb 3, 2024
truecharts-admin
added a commit
to truecharts/charts
that referenced
this issue
Feb 12, 2024
….0 by renovate (#18178) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.7.0-cublas-cuda11-ffmpeg-core` -> `v2.8.0-cublas-cuda11-ffmpeg-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.7.0-cublas-cuda11-core` -> `v2.8.0-cublas-cuda11-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.7.0-cublas-cuda12-ffmpeg-core` -> `v2.8.0-cublas-cuda12-ffmpeg-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.7.0-cublas-cuda12-core` -> `v2.8.0-cublas-cuda12-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.7.0-ffmpeg-core` -> `v2.8.0-ffmpeg-core` | | [docker.io/localai/localai](https://togithub.com/mudler/LocalAI) | minor | `v2.7.0` -> `v2.8.0` | --- > [!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> ### [`v2.8.0`](https://togithub.com/mudler/LocalAI/releases/tag/v2.8.0) [Compare Source](https://togithub.com/mudler/LocalAI/compare/v2.7.0...v2.8.0) This release adds support for Intel GPUs, and it deprecates old ggml-based backends which are by now superseded by llama.cpp (that now supports more architectures out-of-the-box). See also [mudler/LocalAI#1651. Images are now based on Ubuntu 22.04 LTS instead of Debian bullseye. ##### Intel GPUs There are now images tagged with "sycl". There are sycl-f16 and sycl-f32 images indicating f16 or f32 support. For example, to start phi-2 with an Intel GPU it is enough to use the container image like this: docker run -e DEBUG=true -ti -v $PWD/models:/build/models -p 8080:8080 -v /dev/dri:/dev/dri --rm quay.io/go-skynet/local-ai:master-sycl-f32-ffmpeg-core phi-2 ##### What's Changed ##### Exciting New Features 🎉 - feat(sycl): Add support for Intel GPUs with sycl ([#​1647](https://togithub.com/mudler/LocalAI/issues/1647)) by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#1660 - Drop old falcon backend (deprecated) by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#1675 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1678 - Drop ggml-based gpt2 and starcoder (supported by llama.cpp) by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#1679 - fix(Dockerfile): sycl dependencies by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#1686 - feat: Use ubuntu as base for container images, drop deprecated ggml-transformers backends by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#1689 ##### 👒 Dependencies - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1656 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1665 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1669 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1673 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1683 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1688 - ⬆️ Update mudler/go-stable-diffusion by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1674 ##### Other Changes - ⬆️ Update docs version mudler/LocalAI by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1661 - feat(mamba): Add bagel-dpo-2.8b by [@​richiejp](https://togithub.com/richiejp) in [mudler/LocalAI#1671 - fix (docs): fixed broken links `github/` -> `github.com/` by [@​Wansmer](https://togithub.com/Wansmer) in [mudler/LocalAI#1672 - Fix HTTP links in README.md by [@​vfiftyfive](https://togithub.com/vfiftyfive) in [mudler/LocalAI#1677 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1681 - ci: cleanup worker before run by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#1685 - Revert "fix(Dockerfile): sycl dependencies" by [@​mudler](https://togithub.com/mudler) in [mudler/LocalAI#1687 - ⬆️ Update ggerganov/llama.cpp by [@​localai-bot](https://togithub.com/localai-bot) in [mudler/LocalAI#1691 ##### New Contributors - [@​richiejp](https://togithub.com/richiejp) made their first contribution in [mudler/LocalAI#1671 - [@​Wansmer](https://togithub.com/Wansmer) made their first contribution in [mudler/LocalAI#1672 - [@​vfiftyfive](https://togithub.com/vfiftyfive) made their first contribution in [mudler/LocalAI#1677 **Full Changelog**: mudler/LocalAI@v2.7.0...v2.8.0 </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 these updates 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:eyJjcmVhdGVkSW5WZXIiOiIzNy4xODMuMCIsInVwZGF0ZWRJblZlciI6IjM3LjE4My4wIiwidGFyZ2V0QnJhbmNoIjoibWFzdGVyIn0=-->
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Is your feature request related to a problem? Please describe.
There are several backends that would be legacy by now, as
llama.cppenhanced support for different architectures viaggmlover time.Some of them include falcon-ggml and dolly for instance.
This card is about removing support for old backends, not for removing support family (for instance, starcoder is supported by llama.cpp, so no need to have a starcoder backend based out of ggml).
Tracked in #1126
The text was updated successfully, but these errors were encountered: