ollama/create
Daniel Hiltgen a00d083bb5
mlx: System one support (#18701)
* 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>
2026-10-03 13:17:21 -07:00
..
blockfp8.go
blockfp8_test.go
classify.go
classify_test.go
clef.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
clef_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
cohere2moe.go
create.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
create_test.go
draft.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
draft_test.go
gemma4.go
gemma4_test.go
glimmer.go
glimmer_test.go
inventory.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
inventory_test.go
laguna.go
laguna_test.go
laya.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
laya_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
manifest.go Merge remote-tracking branch 'upstream/main' into release_v0.40.0 2026-09-29 11:15:31 -07:00
manifest_test.go
metadata.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
metadata_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
mlxthread.go
nemotron_h.go nemotron_h: add MLX vision support (#17714) 2026-09-17 16:29:14 -07:00
nemotron_h_test.go
pipeline.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
pipeline_test.go
plan.go
plan_test.go
prequant.go
prequant_test.go
quantize.go
quantpolicy.go
qwen4_exp.go
qwen4_exp_test.go
qwen35.go
qwen35_decision.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
qwen35_decision_test.go mlx: System one support (#18701) 2026-10-03 13:17:21 -07:00
transform.go
verify.go
verify_test.go
writer.go
writer_test.go