ollama/types/model
Daniel Hiltgen cecac8bf1b
mlxrunner: add Inkling 2 Mini (#19799)
* mlxrunner: add Inkling 2 Mini

* mlx: fuse Inkling 2 Mini residual mixing on Metal

Fuse RMS normalization and query scoring in one kernel. Apply the
softmax weights in a second kernel to avoid storing per-query products.

* create: expose Inkling 2 Mini context length in model metadata

Copy model_max_length to max_position_embeddings during import so
ollama show reports the checkpoint's context length. Reject configs
that specify conflicting limits.

* mlxrunner: reduce Metal dispatches in Inkling 2 Mini decode

Reuse the prefill mask shader to compute relative position bias in one
dispatch for single-query attention. On M3 Ultra with Metal 3, compute
the loop controller's gain and forget projections in one matrix multiply.
2026-11-20 18:38:44 -08:00
..
testdata/fuzz/FuzzName types/model: overhaul Name and Digest types (#3924) 2024-04-26 13:08:32 -07:00
capability.go mlxrunner: add Phonon text-to-speech support (#19166) 2026-10-22 11:36:42 -07:00
config.go mlx: add LFM3 and d1 models (#19333) 2026-10-27 08:47:18 -07:00
generation.go API: Deprecate typical_p (#18448) 2026-09-14 21:24:26 -07:00
generation_test.go API: Deprecate typical_p (#18448) 2026-09-14 21:24:26 -07:00
name.go Clean up the manifest and modelpath (#13807) 2026-01-21 11:46:17 -08:00
name_test.go Clean up the manifest and modelpath (#13807) 2026-01-21 11:46:17 -08:00
structured.go mlxrunner: add Inkling 2 Mini (#19799) 2026-11-20 18:38:44 -08:00
thinking.go api: expose model thinking levels and defaults (#18473) 2026-09-18 14:10:53 -07:00
thinking_test.go api: expose model thinking levels and defaults (#18473) 2026-09-18 14:10:53 -07:00