gen-cards: add Use-it markers
Browse files
README.md
CHANGED
|
@@ -22,6 +22,9 @@ Apple **Core AI** (`.aimodel`) conversion of [zai-org/GLM-4.7-Flash](https://hug
|
|
| 22 |
Part of the community Core AI model zoo: **https://github.com/john-rocky/coreai-model-zoo**
|
| 23 |
(full card: [`zoo/glm-4.7-flash.md`](https://github.com/john-rocky/coreai-model-zoo/blob/main/zoo/glm-4.7-flash.md)).
|
| 24 |
|
|
|
|
|
|
|
|
|
|
| 25 |
## The `gather_qmm` kernel — 20.3 → 52.4 tok/s (2.6×)
|
| 26 |
|
| 27 |
Apple's `GatherMM` reads **all 64 experts' weights every token**; a custom
|
|
|
|
| 22 |
Part of the community Core AI model zoo: **https://github.com/john-rocky/coreai-model-zoo**
|
| 23 |
(full card: [`zoo/glm-4.7-flash.md`](https://github.com/john-rocky/coreai-model-zoo/blob/main/zoo/glm-4.7-flash.md)).
|
| 24 |
|
| 25 |
+
<!-- gen-cards:use-it begin id=glm-4.7-flash (managed by scripts/gen-cards — edit cards.json / QuickStart.swift, not this block) -->
|
| 26 |
+
<!-- gen-cards:use-it end -->
|
| 27 |
+
|
| 28 |
## The `gather_qmm` kernel — 20.3 → 52.4 tok/s (2.6×)
|
| 29 |
|
| 30 |
Apple's `GatherMM` reads **all 64 experts' weights every token**; a custom
|