Split Q,K,V vs Fused QKV Projections in diffusers Discussion

`diffusers` generally splits fused QKV projections to separate Q, K, V projections in its checkpoint format (for example, for diffusion transformer models). I am interested in collecting feedback on this design choice and any problems which may arise from it. To be honest upfront, I think it is unlikely that we will change this design in the near future, but we would appreciate your feedback nevertheless.

EDIT: the reasoning for using split Q, K, V projections is described in more detail in https://github.com/huggingface/diffusers/issues/14003#issuecomment-4774944332.

Start with the issue body and the linked comment, which explain the split Q, K, V versus fused QKV checkpoint-design rationale. No files, tests, entry points, implementation target, or completion criteria are identified; done is not defined beyond collecting feedback on the design.

Scritto dal modello di indicizzazione a partire dal testo della issue.