auto-round
f17d9cd4
- feat: add per-head fp8 kv attention calibration (#2044)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
5 days ago
feat: add per-head fp8 kv attention calibration (#2044) Signed-off-by: Zeel <desaizeel2128@gmail.com> Co-authored-by: yiliu30 <yi4.liu@intel.com> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
References
#2044 - feat: add per-head fp8 kv attention calibration
Author
zeel2104
Parents
f8ad63f4
Loading