mirrors/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-05-11 10:26:53 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

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
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
57 changed files with 475427 additions and 494 deletions
Download patch file Download diff file Expand all files Collapse all files

6
server/routes_test.go
View file

@ -21,7 +21,7 @@ import (
"unicode"
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/llm"
"github.com/ollama/ollama/fs/ggml"
"github.com/ollama/ollama/openai"
"github.com/ollama/ollama/types/model"
"github.com/ollama/ollama/version"
@ -654,8 +654,8 @@ func TestShow(t *testing.T) {
var s Server
_, digest1 := createBinFile(t, llm.KV{"general.architecture": "test"}, nil)
_, digest2 := createBinFile(t, llm.KV{"general.type": "projector", "general.architecture": "clip"}, nil)
_, digest1 := createBinFile(t, ggml.KV{"general.architecture": "test"}, nil)
_, digest2 := createBinFile(t, ggml.KV{"general.type": "projector", "general.architecture": "clip"}, nil)
createRequest(t, s.CreateHandler, api.CreateRequest{
Name: "show-model",