Fix Gemma3 and Gemma2 flops computation.

[gagika]

Description

• Add correct local attention flops for Gemma3
• Change both gemma2 and gemma3 to use causal attention flops (total attention flops / 2).

Checklist

Before submitting this PR, please make sure (put X in square brackets):

• I have performed a self-review of my code.
• I have necessary comments in my code, particularly in hard-to-understand areas.
• I have run end-to-end tests tests and provided workload links above if applicable.
• I have made or will make corresponding changes to the doc if needed.

[gobbleturk]

Thanks gagik!