* feat(openresponses): support reasoning blocks
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* allow to disable reasoning, refactor common logic
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add option to only strip reasoning
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add configurations for custom reasoning tokens
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(docs): Add Crush and VoxInput to the integrations
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Richard Palethorpe <io@richiejp.com>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* feat: allow to set forcing backends eviction while requests are in flight
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: try to make the request sit and retry if eviction couldn't be done
Otherwise calls that in order to pass would need to shutdown other
backends would just fail.
In this way instead we make the request sit and retry eviction until it
succeeds. The thresholds can be configured by the user.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* add tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* expose settings to CLI
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(loader): refactor single active backend support to LRU
This changeset introduces LRU management of loaded backends. Users can
set now a maximum number of models to be loaded concurrently, and, when
setting LocalAI in single active backend mode we set LRU to 1 for
backward compatibility.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: add tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The internal echo command in sh does not support "-e" and "-E" options
and interprets backslash escape sequences by default. So we prefer the
external echo command when it is available.
Actually it is not necessary to remove particularly the local-ai data
directory before user deletion. It will be accomplished automatically by
the userdel command. But it is crucial to remove additional users from
the local-ai group to allow userdel command to delete the group itself.
* More appropriate place for data storing
The /usr/share subtree in Linux is used for data that generally are not
supposed to change. Conventional places for changeable data are usually
located under /var, so /var/lib seems to be a reasonable default here.
* Data paths consistency fix
* Directory name consistency fix
* feat(ui): add watchdog settings
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Do not re-read env
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Some refactor, move other settings to runtime (p2p)
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add API Keys handling
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Allow to disable runtime settings
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Documentation
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Small fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* show MCP toggle in index
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Drop context default
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Initial plan
* Fix SSE streaming format to comply with specification
- Replace json.Encoder with json.Marshal for explicit formatting
- Use explicit \n\n for all SSE messages (instead of relying on implicit newlines)
- Change %v to %s format specifier for proper string formatting
- Fix error message streaming to include proper SSE format
- Ensure consistency between chat.go and completion.go endpoints
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
* Add proper error handling for JSON marshal failures in streaming
- Handle json.Marshal errors explicitly in error response paths
- Add fallback simple error message if marshal fails
- Prevents sending 'data: <nil>' on marshal failures
- Addresses code review feedback
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
* Fix SSE streaming format to comply with specification
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
* Fix finish_reason field to use pointer for proper null handling
- Change FinishReason from string to *string in Choice schema
- Streaming chunks now omit finish_reason (null) instead of empty string
- Final chunks properly set finish_reason to "stop", "tool_calls", etc.
- Remove empty content from initial streaming chunks (only send role)
- Final streaming chunk sends empty delta with finish_reason
- Addresses OpenAI API compliance issues causing client failures
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
* Improve code consistency for string pointer creation
- Use consistent pattern: declare variable then take address
- Remove inline anonymous function for better readability
- Addresses code review feedback
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
* Move common finish reasons to constants
- Create constants.go with FinishReasonStop, FinishReasonToolCalls, FinishReasonFunctionCall
- Replace all string literals with constants in chat.go, completion.go, realtime.go
- Improves code maintainability and prevents typos
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
* Make it build
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fix finish_reason to always be present with null or string value
- Remove omitempty from FinishReason field in Choice struct
- Explicitly set FinishReason to nil for all streaming chunks
- Ensures finish_reason appears as null in JSON for streaming chunks
- Final chunks still properly set finish_reason to "stop", "tool_calls", etc.
- Complies with OpenAI API specification example
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama.cpp): expose env vars as options for consistency
This allows to configure everything in the YAML file of the model rather
than have global configurations
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat(llama.cpp): respect usetokenizertemplate and use llama.cpp templating system to process messages
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* WIP
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Detect template exists if use tokenizer template is enabled
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Better recognization of chat
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixes to support tool calls while using templates from tokenizer
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Drop template guessing, fix passing tools to tokenizer
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Extract grammar and other options from chat template, add schema struct
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* WIP
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* WIP
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Automatically set use_jinja
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Cleanups, identify by default gguf models for chat
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Added download instructions for macOS DMG file and updated command for Linux and macOS.
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* fix: properly terminate kv_overrides array with empty key
The llama model loading function expects KV overrides to be terminated
with an empty key (key[0] == 0). Previously, the kv_overrides vector was
not being properly terminated, causing an assertion failure.
This commit ensures that after parsing all KV override strings, we add a
final terminating entry with an empty key to satisfy the C-style array
termination requirement. This fixes the assertion error and allows the
model to load correctly with custom KV overrides.
Fixes#6643
- Also included a reference to the usage of the `overrides` option in
the advanced-usage section.
Signed-off-by: blob42 <contact@blob42.xyz>
* doc: document the `overrides` option
---------
Signed-off-by: blob42 <contact@blob42.xyz>
* feat(neutts): add backend
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(ci): add images to CI
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(gallery): add Neutts
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Make it work with quantized versions
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fixups
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* Apply suggestion from @mudler
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* WIP - add endpoint
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Rename
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Wire the Completion API
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Try to make it functional
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Almost functional
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Bump golang versions used in tests
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Add description of the tool
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Make it working
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Small optimizations
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Cleanup/refactor
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update docs
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
The binary is now named "llama-cpp-rpc-server" for p2p workers.
We also decrease the default token rotation interval, in this way
peer discovery is much more responsive.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* feat: split remaining backends and drop embedded backends
- Drop silero-vad, huggingface, and stores backend from embedded
binaries
- Refactor Makefile and Dockerfile to avoid building grpc backends
- Drop golang code that was used to embed backends
- Simplify building by using goreleaser
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(gallery): be specific with llama-cpp backend templates
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(docs): update
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore(ci): minor fixes
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* chore: drop all ffmpeg references
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix: run protogen-go
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Always enable p2p mode
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Update gorelease file
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* fix(stores): do not always load
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Fix linting issues
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Simplify
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
* Mac OS fixup
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
---------
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
feat: reduce images size and stop bundling sources
Do not copy sources anymore, and reduce packages of the base images by
not using builder images.
If needed to rebuild, just build the container image from scratch by
following the docs. We will slowly try to migrate all backends to the
gallery to keep the core small.
This PR is a breaking change, it also sets the base folders to /models
and /backends instead of /build/models and /build/backends.
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Signed-off-by: Ettore Di Giacinto <mudler@users.noreply.github.com>
* 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>
vulkan docker tag is not prefixed with gpu
```
regctl tag ls localai/localai | grep 2.29 | grep vulkan
v2.29.0-vulkan
```
Signed-off-by: Gavin Mogan <github@gavinmogan.com>
* Add note to help run nvidia containers with SELinux
* Use correct CUDA container references as noted in the dockerhub overview
* Clean trailing whitespaces
* Update installation script for improved compatibility and clarity
- Renamed VERSION to LOCALAI_VERSION to avoid conflicts with system variables.
- Enhanced NVIDIA and CUDA repository installation for DNF5 compatibility.
- Adjusted default Fedora version handling for CUDA installation.
- Updated Docker image tag handling to use LOCALAI_VERSION consistently.
- Improved logging messages for repository and LocalAI binary downloads.
- Added a temporary bypass for nvidia-smi installation on Fedora Cloud Edition.
* feat: Add SELinux configuration for NVIDIA GPU support in containers
- Introduced `enable_selinux_container_booleans` function to handle SELinux configuration changes for GPU access.
- Included user confirmation prompt to enable SELinux `container_use_devices` boolean due to security implications.
- Added NVIDIA Container Runtime to Docker runtimes and restarted Docker to ensure proper GPU support.
- Applied SELinux adjustments conditionally for Fedora, RHEL, CentOS, Rocky, and openSUSE distributions.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* fix: Correct SELinux boolean parsing and add loop break
- Fixed incorrect parsing of `container_use_devices` boolean by changing the awk field from `$2` to `$3` to retrieve the correct value.
- Added a `break` statement after enabling the SELinux boolean to prevent unnecessary loop iterations after user prompt.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* fix: typo in install.sh
Signed-off-by: Alessandro Pirastru <57262788+Bloodis94@users.noreply.github.com>
---------
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
Signed-off-by: Alessandro Pirastru <57262788+Bloodis94@users.noreply.github.com>
* Update installation script for improved compatibility and clarity
- Renamed VERSION to LOCALAI_VERSION to avoid conflicts with system variables.
- Enhanced NVIDIA and CUDA repository installation for DNF5 compatibility.
- Adjusted default Fedora version handling for CUDA installation.
- Updated Docker image tag handling to use LOCALAI_VERSION consistently.
- Improved logging messages for repository and LocalAI binary downloads.
- Added a temporary bypass for nvidia-smi installation on Fedora Cloud Edition.
* Enhance log functions with ANSI color formatting
- Added ANSI escape codes for improved log styling: light blue for info, orange for warnings, and red for errors.
- Updated all log functions (`info`, `warn`, `fatal`) to include bold and colored output.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* feat: Enhance log functions with ANSI color formatting
- Added ANSI escape codes for improved log styling: light blue for info, orange for warnings, and red for errors.
- Updated all log functions (`info`, `warn`, `fatal`) to include bold and colored output.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* chore: ⬆️ Update ggml-org/llama.cpp to `ecda2ec4b347031a9b8a89ee2efc664ce63f599c` (#5238)
⬆️ Update ggml-org/llama.cpp
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
* fix(stablediffusion-ggml): Build with DSD CUDA, HIP and Metal flags (#5236)
Signed-off-by: Richard Palethorpe <io@richiejp.com>
* feat(install): enhance script with choice functions and logs
- Added custom `choice_info`, `choice_warn`, and `choice_fatal` functions for interactive input logging.
- Adjusted Docker volume creation message for better clarity.
- Included NVIDIA driver check log for improved feedback to users.
- Added consistent logging before starting LocalAI Docker containers across configurations.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* feat(install): add Fedora NVIDIA driver installation option
- Introduced a new function to install NVIDIA kernel drivers on Fedora using akmod packages.
- Added user prompt to choose between installing drivers automatically or exiting for manual setup.
- Integrated the new function into the existing Fedora-specific CUDA toolkit installation workflow.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* fix(install): correct repository ID for DNF5 configuration
- Update repository ID from 'nome-repo' to 'nvidia-cuda' for DNF5.
- Ensures the correct repository name matches expected configuration.
- Fix prevents potential misconfiguration during installation process.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* feat(install): enhance NVIDIA driver handling on Fedora
- fixed `install_cuda_driver_yum` function call in `install_fedora_nvidia_kernel_drivers`
- Added `cuda-toolkit` for Fedora installations, as recommended by RPM Fusion.
- Adjusted driver repository commands for compatibility with DNF5.
- Improved URL and version handling for package manager installations.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* Refactor NVIDIA driver installation process in install.sh
- Removed redundant empty lines for cleaner formatting.
- Standardized URL formatting by removing unnecessary quotes around URLs.
- Reverted logic by removing Fedora-specific exclusions for cuda-toolkit and using `cuda-drivers` universally.
- Refined repository addition for `dnf` by explicitly setting `id` and `name` parameters for clarity and accuracy.
- Fixed minor formatting inconsistencies in parameter passing.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* feat: Update NVIDIA module installation warning in install script
- Clarified that Akmod installation may inhibit the reboot command.
- Added a cautionary note to the warning to inform users of potential risks.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
* Update NVIDIA driver installation warning message
- Clarify prerequisites by noting the need for rpmfusion free/nonfree repos.
- Improve formatting of the warning box for better readability.
- Inform users that the script will install missing repos if necessary.
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
---------
Signed-off-by: Alessandro Pirastru <alessandro.pirastru.94@gmail.com>
Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Signed-off-by: Richard Palethorpe <io@richiejp.com>
Co-authored-by: LocalAI [bot] <139863280+localai-bot@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>
Co-authored-by: Richard Palethorpe <io@richiejp.com>
Update installation script for improved compatibility and clarity
- Renamed VERSION to LOCALAI_VERSION to avoid conflicts with system variables.
- Enhanced NVIDIA and CUDA repository installation for DNF5 compatibility.
- Adjusted default Fedora version handling for CUDA installation.
- Updated Docker image tag handling to use LOCALAI_VERSION consistently.
- Improved logging messages for repository and LocalAI binary downloads.
- Added a temporary bypass for nvidia-smi installation on Fedora Cloud Edition.
The GGML format is now dead, since in the next version of LocalAI we
already bring many breaking compatibility changes, taking the occasion
also to drop ggml support (pre-gguf).
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
