ollama/model/renderers/testdata
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
..
d3_chat_template.jinja mlx: add d3 decision model support (#19196) 2026-10-22 08:50:14 -07:00
d3_edge_chat_template.jinja mlx: add d3 decision model support (#19196) 2026-10-22 08:50:14 -07:00
d3_mini_chat_template.jinja mlx: add d3 decision model support (#19196) 2026-10-22 08:50:14 -07:00
flint_chat_template.jinja flint: fix replies with thinking disabled (#19216) 2026-10-22 11:38:27 -07:00
gemma4_31b_chat_template.jinja2 model: align gemma4 chat template handling (#17182) 2026-07-14 15:42:04 -07:00
gemma4_e2b_chat_template.jinja2 model: align gemma4 chat template handling (#17182) 2026-07-14 15:42:04 -07:00
gemma4_nemotron_chat_template.jinja2 Update gemma renderers (#19241) 2026-10-23 07:12:11 -07:00
glimmer_chat_template.jinja model/renderers: match Muse Glimmer reasoning template (#17732) 2026-08-13 14:35:50 -07:00
inkling2_chat_template.jinja mlxrunner: add Inkling 2 Mini (#19799) 2026-11-20 18:38:44 -08:00
laguna_v2_chat_template.jinja2 model: add Laguna v8 chat support and fix Metal inference (#17291) 2026-07-21 16:06:29 -07:00
laguna_v8_chat_template.jinja2 model: add Laguna v8 chat support and fix Metal inference (#17291) 2026-07-21 16:06:29 -07:00
lfm3_audio_chat_template.jinja2 mlx: add LFM3 and d1 models (#19333) 2026-10-27 08:47:18 -07:00
lfm3_chat_template.jinja2 mlx: add LFM3 and d1 models (#19333) 2026-10-27 08:47:18 -07:00
lfm3_omni_chat_template.jinja2 mlx: add LFM3 and d1 models (#19333) 2026-10-27 08:47:18 -07:00
mimo_v26_chat_template.jinja model: add MiMo V2.6 renderer for Qwen3.5 (#19400) 2026-11-03 07:09:06 -08:00
nemotron3nano_chat_template.jinja2 mlx: implement Nemotron 3 Nano Omni (#17060) 2026-08-10 21:42:34 -07:00
nemotron35_chat_template.jinja2 nemotron_h: support the Nemotron 3.5 prompt layout (#17672) 2026-08-11 06:18:51 -07:00
qwen38_chat_template.jinja qwen3.8: add renderer and MLX import support (#17745) 2026-08-14 09:31:09 -07:00
ripple_chat_template.jinja Add ripple preview support to the MLX runner (#19592) 2026-11-07 16:36:53 -08:00