Patch release v4.46.2

Mostly had to finish the gradient accumulation ! Thanks to @techkang and @Ryukijano 🤗

• VLMs: fix number of image tokens (#34332) by @zucchini-nlp
• fix pixtral processor (#34486) by @@molbap
• enable average tokens across devices (#34373) by @techkang and @muellerzr
• Update trainer for easier handling of accumulate, compile fixes, and … by @muellerzr and @Ryukijano
• MPS: isin_mps_friendly can support 0D tensors (#34538) by @gante