matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-14 01:37:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

next ollama runner (#7913)

Browse Source 
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>
This commit is contained in:
Michael Yang
2025-02-14 00:31:21 +00:00
committed by GitHub
parent 8cf16063a5
commit 58245413f4
57 changed files with 475427 additions and 494 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
server/model.go
View File

@@ -15,7 +15,7 @@ import (
"text/template/parse"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/llm"
"github.com/ollama/ollama/fs/ggml"
"github.com/ollama/ollama/template"
"github.com/ollama/ollama/types/model"
)
@@ -24,7 +24,7 @@ var intermediateBlobs map[string]string = make(map[string]string)
type layerGGML struct {
Layer
*llm.GGML
*ggml.GGML
}
func parseFromModel(ctx context.Context, name model.Name, fn func(api.ProgressResponse)) (layers []*layerGGML, err error) {
@@ -64,12 +64,12 @@ func parseFromModel(ctx context.Context, name model.Name, fn func(api.ProgressRe
}
defer blob.Close()
ggml, _, err := llm.DecodeGGML(blob, 0)
f, _, err := ggml.Decode(blob, 0)
if err != nil {
return nil, err
}
layers = append(layers, &layerGGML{layer, ggml})
layers = append(layers, &layerGGML{layer, f})
default:
layers = append(layers, &layerGGML{layer, nil})
}
@@ -118,7 +118,7 @@ func detectContentType(r io.Reader) (string, error) {
return "", err
}
if contentType := llm.DetectGGMLType(b.Bytes()); contentType != "" {
if contentType := ggml.DetectContentType(b.Bytes()); contentType != "" {
return contentType, nil
}