Gemma4

This hotfix release addresses issues from the yanked v5.10.0, introduces several new multimodal and specialized models (Gemma4 Unified, Sapiens2, DeepSeek-OCR-2, Mellum), and includes significant fixes for model parallelism and quantization.

This release introduces several new models, including Cohere2Moe and HRM-Text, alongside significant improvements in audio processing and generation stability. Breaking changes affect input expectations for SAM3 family models.

This release introduces two major new model families, Laguna and DEIMv2, alongside numerous fixes for attention mechanisms, continuous batching generation, and kernel loading across various models.

A small patch release addressing an issue with device map auto support specifically for Gemma4 models.

This release focuses heavily on DeepSeek V4 maturity with new kernel support and packaging, significant advancements in Model Runner V2, and the introduction of an experimental Rust frontend. Performance saw notable gains from batch-invariant inference with Cutlass FP8 and the rollout of multi-tier KV cache offloading.