Fix broadcast crash in quantized SDPA with GQA + batched padding mask (batch >= 2)#1467

angeloskath merged 2 commits into

ml-explore:mainml-explore/mlx-lm:mainfrom

pinglin:fix-quantized-sdpa-gqa-batched-maskpinglin/mlx-lm:fix-quantized-sdpa-gqa-batched-maskCopy head branch name to clipboard