next ollama runner (#7913)

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>

template/template_test.go

@@ -14,7 +14,7 @@ import (
 	"github.com/google/go-cmp/cmp"
 
 	"github.com/ollama/ollama/api"
-	"github.com/ollama/ollama/llm"
+	"github.com/ollama/ollama/fs/ggml"
 )
 
 func TestNamed(t *testing.T) {
@@ -33,7 +33,7 @@ func TestNamed(t *testing.T) {
 
 		for k, v := range ss {
 			t.Run(k, func(t *testing.T) {
-				kv := llm.KV{"tokenizer.chat_template": v}
+				kv := ggml.KV{"tokenizer.chat_template": v}
 				s := kv.ChatTemplate()
 				r, err := Named(s)
 				if err != nil {