matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-10 07:46:59 +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

12
convert/convert_test.go
View File

@@ -20,7 +20,7 @@ import (
"golang.org/x/exp/maps"
"github.com/ollama/ollama/llm"
"github.com/ollama/ollama/fs/ggml"
)
type tensorData struct {
@@ -29,7 +29,7 @@ type tensorData struct {
Shape []int `json:"shape"`
}
func convertFull(t *testing.T, fsys fs.FS) (*os.File, llm.KV, *llm.Tensors) {
func convertFull(t *testing.T, fsys fs.FS) (*os.File, ggml.KV, ggml.Tensors) {
t.Helper()
f, err := os.CreateTemp(t.TempDir(), "f16")
@@ -48,7 +48,7 @@ func convertFull(t *testing.T, fsys fs.FS) (*os.File, llm.KV, *llm.Tensors) {
}
t.Cleanup(func() { r.Close() })
m, _, err := llm.DecodeGGML(r, math.MaxInt)
m, _, err := ggml.Decode(r, math.MaxInt)
if err != nil {
t.Fatal(err)
}
@@ -60,7 +60,7 @@ func convertFull(t *testing.T, fsys fs.FS) (*os.File, llm.KV, *llm.Tensors) {
return r, m.KV(), m.Tensors()
}
func generateResultsJSON(t *testing.T, f *os.File, kv llm.KV, tensors *llm.Tensors) map[string]string {
func generateResultsJSON(t *testing.T, f *os.File, kv ggml.KV, tensors ggml.Tensors) map[string]string {
actual := make(map[string]string)
for k, v := range kv {
if s, ok := v.(json.Marshaler); !ok {
@@ -75,7 +75,7 @@ func generateResultsJSON(t *testing.T, f *os.File, kv llm.KV, tensors *llm.Tenso
}
}
for _, tensor := range tensors.Items {
for _, tensor := range tensors.Items() {
sha256sum := sha256.New()
sr := io.NewSectionReader(f, int64(tensors.Offset+tensor.Offset), int64(tensor.Size()))
if _, err := io.Copy(sha256sum, sr); err != nil {
@@ -332,7 +332,7 @@ func TestConvertAdapter(t *testing.T) {
}
defer r.Close()
m, _, err := llm.DecodeGGML(r, math.MaxInt)
m, _, err := ggml.Decode(r, math.MaxInt)
if err != nil {
t.Fatal(err)
}