mirror of
https://github.com/ollama/ollama.git
synced 2026-11-22 00:01:45 +00:00
* 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.
11 lines
337 B
Go
11 lines
337 B
Go
package model
|
|
|
|
// StructuredOutputFrames describes the markers a model can emit before a
|
|
// structured answer. A thinking close without an open continues a thought
|
|
// the template already opened.
|
|
type StructuredOutputFrames struct {
|
|
ThinkingOpen string
|
|
ThinkingClose string
|
|
ThinkingExcludes []string
|
|
ContentOpen string
|
|
}
|