fix: bug with gemma cache on non-fp32

[chanind]

Currently, gemma2 throws an error when using a dtype other than fp32 with caching. This PR sets the cache dtype to match the model dtype.

[codecov-commenter]

⚠️ Please install the to ensure uploads and comments are reliably processed by Codecov.

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 90.63%. Comparing base (18a7bfc) to head (bd987c7).
Report is 2 commits behind head on main.

❗ Your organization needs to install the Codecov GitHub app to enable full functionality.

Additional details and impacted files

@@            Coverage Diff             @@
##             main      #10      +/-   ##
==========================================
+ Coverage   90.62%   90.63%   +0.01%     
==========================================
  Files          20       20              
  Lines        1045     1047       +2     
==========================================
+ Hits          947      949       +2     
  Misses         98       98              

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.