mirror of
https://github.com/ollama/ollama.git
synced 2026-02-08 14:43:05 -05:00
33ee7168ba
* 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>
30 lines
705 B
Go
30 lines
705 B
Go
package nn
|
|
|
|
import (
|
|
"github.com/ollama/ollama/x/ml"
|
|
)
|
|
|
|
type LayerNorm struct {
|
|
Weight ml.Tensor `gguf:"weight"`
|
|
Bias ml.Tensor `gguf:"bias"`
|
|
}
|
|
|
|
func (m *LayerNorm) Forward(ctx ml.Context, t ml.Tensor, eps float32) ml.Tensor {
|
|
return t.LayerNorm(ctx, m.Weight, m.Bias, eps)
|
|
}
|
|
|
|
type RMSNorm struct {
|
|
Weight ml.Tensor `gguf:"weight"`
|
|
}
|
|
|
|
func (m *RMSNorm) Forward(ctx ml.Context, t ml.Tensor, eps float32) ml.Tensor {
|
|
// slog.Info("RMSNorm", "eps", eps)
|
|
// fmt.Fprintln(os.Stderr, t.ToString())
|
|
// fmt.Fprintln(os.Stderr, m.Weight.ToString())
|
|
|
|
// TODO this is probably model specific, not generalized...
|
|
w := m.Weight.Add(ctx, ctx.FromFloats([]float32{1.0}, 1))
|
|
|
|
return t.RMSNorm(ctx, w, eps)
|
|
}
|