mirror of
https://github.com/zebrajr/ollama.git
synced 2025-12-06 00:19:51 +01:00
58245413f4
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> |
||
|---|---|---|
| .. | ||
| testdata/tools | ||
| auth.go | ||
| create.go | ||
| download.go | ||
| fixblobs_test.go | ||
| fixblobs.go | ||
| images.go | ||
| layer.go | ||
| manifest_test.go | ||
| manifest.go | ||
| model_test.go | ||
| model.go | ||
| modelpath_test.go | ||
| modelpath.go | ||
| prompt_test.go | ||
| prompt.go | ||
| routes_create_test.go | ||
| routes_delete_test.go | ||
| routes_generate_test.go | ||
| routes_list_test.go | ||
| routes_test.go | ||
| routes.go | ||
| sched_test.go | ||
| sched.go | ||
| sparse_common.go | ||
| sparse_windows.go | ||
| upload.go | ||