mirror of
https://github.com/ollama/ollama.git
synced 2026-11-12 03:46:14 -06:00
a00d083bb5
* mlxrunner: restore System One scoring
Carry the MLX implementation and its tests from the original System One
commit. The API/compiler and llama-server implementation already exist on
the release branch, so retain those versions. Adapt the optional model test
to the renamed decision package and its explicit rendering/context setup.
(cherry picked from commit 26e546ddb3)
* Enable MLX System One and add regression coverage
* mlxrunner: add Laya support for System One
Import Laya checkpoints and implement bidirectional decision scoring.
* mlxrunner: release cached buffers after System One scoring
* decision: match Tev1 and Nimble publisher prompt formats
Select Tev1 prompts using renderer metadata and fix JSON formatting, with regression coverage for GGUF and MLX.
* mlx: support Clef and Clef Flash decision models
Add model import, quantization safeguards, and text/image scoring with the Clef joint decision head.
* support vision capabilities for decision models
* Make Clef scoring cancellable between prefill chunks
Preserve joint-head inputs and test cancellation, cleanup, and recovery.
* mlx: separate decision preparation and readout from forward
Let serial and batched scoring share model-owned preparation and readout
without duplicating architecture-specific logic in the runner.
* mlx: add Strands Decider support
* implement caching
---------
Co-authored-by: ParthSareen <parth.sareen@ollama.com>
66 lines
1.7 KiB
Go
66 lines
1.7 KiB
Go
// Package mlxtest provides shared scaffolding for tests that exercise MLX
|
|
// through the cgo wrapper in mlx.
|
|
package mlxtest
|
|
|
|
import (
|
|
"sync"
|
|
"testing"
|
|
|
|
"github.com/ollama/ollama/mlx"
|
|
"github.com/ollama/ollama/mlx/mlxthread"
|
|
"github.com/ollama/ollama/mlx/mlxthread/mlxthreadtest"
|
|
)
|
|
|
|
var testThread = sync.OnceValues(func() (*mlxthreadtest.Thread, error) {
|
|
return mlxthreadtest.Start("mlx-test", func() error {
|
|
if err := mlx.CheckInit(); err != nil {
|
|
return err
|
|
}
|
|
if mlx.GPUIsAvailable() {
|
|
mlx.SetDefaultDeviceGPU()
|
|
}
|
|
return nil
|
|
})
|
|
})
|
|
|
|
// T is the test state available to callbacks running on the MLX thread.
|
|
type T = mlxthreadtest.T
|
|
|
|
// Worker returns the shared worker for handlers that dispatch their own MLX
|
|
// jobs. Call them outside Run; the shared worker must not be stopped by a test.
|
|
func Worker(t testing.TB) *mlxthread.Thread {
|
|
t.Helper()
|
|
thread, err := testThread()
|
|
if err != nil {
|
|
t.Skipf("MLX not available: %v", err)
|
|
}
|
|
return thread.Worker()
|
|
}
|
|
|
|
// SkipIfUnavailable skips the test when the MLX dynamic library cannot be
|
|
// loaded (e.g. no MLX backend built for this platform).
|
|
func SkipIfUnavailable(t *testing.T) {
|
|
t.Helper()
|
|
if _, err := testThread(); err != nil {
|
|
t.Skipf("MLX not available: %v", err)
|
|
}
|
|
}
|
|
|
|
// Run executes fn on the MLX thread shared by the package's test binary.
|
|
func Run(t *testing.T, fn func(*T)) {
|
|
t.Helper()
|
|
|
|
thread, err := testThread()
|
|
if err != nil {
|
|
t.Skipf("MLX not available: %v", err)
|
|
}
|
|
|
|
mlxthreadtest.Run(t, thread, fn)
|
|
}
|
|
|
|
// RunSubtest runs a named subtest on the shared MLX test thread.
|
|
func RunSubtest(t *testing.T, name string, fn func(*T)) {
|
|
t.Helper()
|
|
t.Run(name, func(t *testing.T) { Run(t, fn) })
|
|
}
|