Published March 24, 2026
| Version v1
Preprint
Open
Grouped-Query Attention — Cache-Efficient Architecture Design
Description
Research article: Grouped-Query Attention — Cache-Efficient Architecture Design
Files
gqa-cache-efficient.md
Files
(20.8 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:d22133ce0bf100cc67779c385f201c7f
|
20.8 kB | Preview Download |