6 Commits

Author SHA1 Message Date
Parth Sareen
7e34f4fbfa
sample: add numerical stability to temperature/softmax transform (#9631) 2025-03-10 14:43:53 -07:00
Jeffrey Morgan
e093db92c4
sample: temporarily use grammars for constrained generation in new engine (#9586) 2025-03-10 16:17:39 +01:00
Parth Sareen
0682dae027
sample: improve ollama engine sampler performance (#9374)
This change bring in various interface cleanups along with greatly improving the performance of the sampler.

Tested with llama3.2 on local machine.
Improves performance from ~ 70 tokens/s -> 135 tokens/s with topK(40) enabled.
Without topK performance is ~ 110 tokens/s
2025-03-07 12:37:48 -08:00
Parth Sareen
c245b0406f
sample: remove transforms from greedy sampling (#9377) 2025-02-27 15:44:53 -08:00
Parth Sareen
0b7e1676eb
sample: add sampling package for new engine (#8410) 2025-02-24 17:19:01 -08:00
Michael Yang
58245413f4
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>
2025-02-13 16:31:21 -08:00