GitLab

feat: add new Ollama engine using ggml through cgo

This change introduces a new way to run pretrained models. It introduces 3 high level interfaces and a bunch of smaller helper interfaces to facilitate this.

- `model.Model` defines the interface for a model architecture. Models such as `llama` and `mllama`, which are provided as examples, can implement the model's forward propagation in the `Forward` method. This method will be called to generate completions. This interface can be found in `model/model.go`
- `ml.Backend` defines the interface for a backend tensor library, in this case `ggml`. Among other things, a Backend is responsible for loading a pretrained model into hardware (GPU, CPU, etc) and providing an interface for Models to access loaded tensors. This interface can be found in `ml/backend.go`
- `ml.Tensor` defines the interface for a tensor and tensor operations

This is the first implementation of the new engine. Follow up PRs will implement more features:

- non-greedy sampling (#8410)
- integration with Ollama and KV caching (#8301)
- more model support (#9080) with more coming soon
Co-authored-by: Bruce MacDonald <brucewmacdonald@gmail.com>

Co-authored-by: Richard Lyons <frob@cloudstaff.com>

removing the channel tag from the url so it will always go to the current stable channel.

* wrap ggml_backend_load_best in try/catch
* ignore non-ollama paths

ollama requires vcruntime140_1.dll which isn't found on 2019. previously
the job used the windows runner (2019) but it explicitly installs
2022 to build the app. since the sign job doesn't actually build
anything, it can use the windows-2022 runner instead.

the find returns intermediate directories which pulls the parent
directories. it also omits files under lib/ollama.

switch back to globbing

Shield the code processing the embedding result
from subsequent calls that may overwrite the same
buffer to process a second input when retrieving
model embeddings.

* chore: update gitattributes
* chore: add build info source

Removed redundant checks and streamlined the switch-case structure.
Added test cases for both HumanBytes and HumanBytes2 to cover a wide range of scenarios.

In some cases, downloads slow due to disk i/o or other factors,
causing the download to restart a part. This causes the download
to "reverse" in percent completion. By increasing the timeout to 30s,
this should happen less frequently.