mirror of
https://github.com/ollama/ollama.git
synced 2026-03-28 03:08:44 +07:00
* WIP - MLX backend with gemma3 * MLX: add cmake and go tag build toggles To build the new MLX backend code: cmake --preset MLX cmake --build --preset MLX --parallel cmake --install build --component MLX go build -tags mlx . Note: the main.go entrypoint for the MLX engine will change in a follow up commit. * add experimental image generation runtime * add experimental image generation runtime * MLX: wire up cuda build for linux * MLX: get dependencies correct and dedup This is still too large for a unified github artifact, but is now "correct" for the mlx_cuda_v13 directory. * fix relative link bug in dedup * Add darwin build and readme * add go build tag for mlx dependent code and wire up build_darwin.sh * lint cleanup * macos: build mlx for x86 This will be CPU only. * cuda build instructions and fix drift from mlx bump * stale comment * Delete agent helper doc * Clean up readme.md * Revise README for tokenizer clarity and details Updated README to clarify tokenizer functionality and removed correctness section. --------- Co-authored-by: jmorganca <jmorganca@gmail.com>
33 lines
641 B
Go
33 lines
641 B
Go
package nn
|
|
|
|
import "github.com/ollama/ollama/x/ml"
|
|
|
|
type Linear struct {
|
|
Weight ml.Tensor `gguf:"weight"`
|
|
Bias ml.Tensor `gguf:"bias"`
|
|
}
|
|
|
|
func (m *Linear) Forward(ctx ml.Context, t ml.Tensor) ml.Tensor {
|
|
t = t.Matmul(ctx, m.Weight.Transpose(ctx))
|
|
if m.Bias != nil {
|
|
t = t.Add(ctx, m.Bias)
|
|
}
|
|
|
|
return t
|
|
}
|
|
|
|
type LinearBatch struct {
|
|
Weight ml.Tensor `gguf:"weight"`
|
|
Bias ml.Tensor `gguf:"bias"`
|
|
}
|
|
|
|
func (m *LinearBatch) Forward(ctx ml.Context, t, indices ml.Tensor) ml.Tensor {
|
|
panic("not yet ported")
|
|
// t = m.Weight.MulmatID(ctx, t, indices)
|
|
// if m.Bias != nil {
|
|
// t = t.AddID(ctx, m.Bias, indices)
|
|
// }
|
|
|
|
// return t
|
|
}
|