auto-round
a52c81ef - Reduce RAM usage of quantizing VLM models and fix issues of quantizing gemma4
Commit
View On GitHub
Commit
2 days ago
Reduce RAM usage of quantizing VLM models and fix issues of quantizing gemma4 Signed-off-by: lvliang-intel <liang1.lv@intel.com>
Author
lvliang-intel lvliang-intel
Committer
lvliang-intel lvliang-intel
Parents
5bbe39ba
FAQ Terms Privacy Refunds Impressum
Loading