mirror of
https://github.com/ollama/ollama.git
synced 2026-01-12 00:06:57 +08:00
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>
59 lines
1.7 KiB
Go
59 lines
1.7 KiB
Go
//go:build mlx
|
|
|
|
package gemma3
|
|
|
|
import (
|
|
"fmt"
|
|
"image"
|
|
_ "image/jpeg"
|
|
_ "image/png"
|
|
"os"
|
|
|
|
"github.com/ollama/ollama/x/imagegen/mlx"
|
|
"golang.org/x/image/draw"
|
|
)
|
|
|
|
// ProcessImage loads and preprocesses an image for the vision tower
|
|
// Returns [1, H, W, C] tensor in NHWC format normalized for SigLIP
|
|
func ProcessImage(path string, imageSize int32) (*mlx.Array, error) {
|
|
f, err := os.Open(path)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("open image: %w", err)
|
|
}
|
|
defer f.Close()
|
|
|
|
img, _, err := image.Decode(f)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("decode image: %w", err)
|
|
}
|
|
|
|
return ProcessImageData(img, imageSize)
|
|
}
|
|
|
|
// ProcessImageData preprocesses an image.Image for the vision tower
|
|
func ProcessImageData(img image.Image, imageSize int32) (*mlx.Array, error) {
|
|
// Resize to target size using bilinear interpolation
|
|
resized := image.NewRGBA(image.Rect(0, 0, int(imageSize), int(imageSize)))
|
|
draw.BiLinear.Scale(resized, resized.Bounds(), img, img.Bounds(), draw.Over, nil)
|
|
|
|
// Convert to float32 array [H, W, C] and normalize
|
|
// SigLIP normalization: (pixel / 255.0 - 0.5) / 0.5 = pixel / 127.5 - 1.0
|
|
data := make([]float32, imageSize*imageSize*3)
|
|
idx := 0
|
|
for y := int32(0); y < imageSize; y++ {
|
|
for x := int32(0); x < imageSize; x++ {
|
|
r, g, b, _ := resized.At(int(x), int(y)).RGBA()
|
|
// RGBA returns 16-bit values, convert to 8-bit
|
|
data[idx] = float32(r>>8)/127.5 - 1.0
|
|
data[idx+1] = float32(g>>8)/127.5 - 1.0
|
|
data[idx+2] = float32(b>>8)/127.5 - 1.0
|
|
idx += 3
|
|
}
|
|
}
|
|
|
|
// Create MLX array [1, H, W, C] for NHWC layout
|
|
arr := mlx.NewArrayFloat32(data, []int32{1, imageSize, imageSize, 3})
|
|
mlx.Eval(arr) // Materialize to prevent use-after-free
|
|
return arr, nil
|
|
}
|