mirror of
https://github.com/ollama/ollama.git
synced 2025-03-20 23:02:48 +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>
12 lines
260 B
Go
12 lines
260 B
Go
package nn
|
|
|
|
import "github.com/ollama/ollama/ml"
|
|
|
|
type Conv2D struct {
|
|
Weight ml.Tensor `gguf:"weight"`
|
|
}
|
|
|
|
func (m *Conv2D) Forward(ctx ml.Context, t ml.Tensor, s0, s1, p0, p1, d0, d1 int) ml.Tensor {
|
|
return m.Weight.Conv2D(ctx, t, s0, s1, p0, p1, d0, d1)
|
|
}
|