starred/ollama-ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-04-17 15:53:27 +02:00
Code Issues Packages Projects Releases Wiki Activity

mlx: Improve M5 performance with NAX (#15345)

Browse Source 
* mlx: Improve M5 performance with NAX

This modifies the Mac release to now have 2 builds of MLX for broader
compatibility while supporting the latest M5 hardware features.  NAX requires
building with xcode 26.2 and targetting support only for OS v26 and up.  Since
we want to support older MacOS versions as well, we now need 2 different MLX
builds and runtime detection logic to select the optimal version.  The newer
build will detect NAX missing at runtime, so it is safe to run on pre M5 macs.

* mac: prevent generate on cross-compiles

For some versions of Xcode, cmake builds are failing due to header problems in
cross-compiling during the generate phase.  Since generate is producing arch
independent generated output, we can skip this during cross-compiling.
This commit is contained in:
Daniel Hiltgen
2026-04-07 08:12:24 -07:00
committed by GitHub
parent 8c8f8f3450
commit 8968740836
7 changed files with 332 additions and 121 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
discover/runner.go
View File

@@ -94,7 +94,7 @@ func GPUDevices(ctx context.Context, runners []ml.FilteredRunnerDiscovery) []ml.
}
var dirs []string
if dir != "" {
if requested != "" && filepath.Base(dir) != requested {
if requested != "" && !strings.HasPrefix(requested, "mlx_") && filepath.Base(dir) != requested {
slog.Debug("skipping available library at user's request", "requested", requested, "libDir", dir)
continue
} else if jetpack != "" && filepath.Base(dir) != "cuda_"+jetpack {