Name Robert P Smith (tcclaviger) as co-author
Browse filesAuthor lines and citations only; the maps and their manifests are unchanged.
README.md
CHANGED
|
@@ -129,12 +129,12 @@ Q3-8B-KVA-Projector, which retrofitted it onto Qwen3-8B with trained key and val
|
|
| 129 |
|
| 130 |
## Citation
|
| 131 |
|
| 132 |
-
The paper, *RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill* by Dylan Johnston and
|
| 133 |
preparation. Until it is out, cite the data release:
|
| 134 |
|
| 135 |
```bibtex
|
| 136 |
@misc{johnston2026ridgefilldata,
|
| 137 |
-
author = {Johnston, Dylan and
|
| 138 |
title = {{RidgeFill}: data and code for ``Training-Free Late-Layer Cache Fill for Faster Prefill''},
|
| 139 |
year = {2026},
|
| 140 |
version = {1.1},
|
|
|
|
| 129 |
|
| 130 |
## Citation
|
| 131 |
|
| 132 |
+
The paper, *RidgeFill: Training-Free Late-Layer Cache Fill for Faster Prefill* by Dylan Johnston and Robert P Smith, is in
|
| 133 |
preparation. Until it is out, cite the data release:
|
| 134 |
|
| 135 |
```bibtex
|
| 136 |
@misc{johnston2026ridgefilldata,
|
| 137 |
+
author = {Johnston, Dylan and Smith, Robert P},
|
| 138 |
title = {{RidgeFill}: data and code for ``Training-Free Late-Layer Cache Fill for Faster Prefill''},
|
| 139 |
year = {2026},
|
| 140 |
version = {1.1},
|