Add per-layer hybrid sliding/full attention (Gemma 3 / Gemma 4) to CoreML static LLM export#19251
Open
john-rocky wants to merge 3 commits intopytorch:mainfrom
Open
Add per-layer hybrid sliding/full attention (Gemma 3 / Gemma 4) to CoreML static LLM export#19251john-rocky wants to merge 3 commits intopytorch:mainfrom
john-rocky wants to merge 3 commits intopytorch:mainfrom