GraniteMoeHybrid

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.

This release introduces several major multimodal and specialized models, including the Qwen2.5-Omni streaming model, the high-precision SAM-HQ segmenter, and the D-FINE real-time object detector.

This release introduces the GraniteMoeHybrid model architecture, a hybrid design combining state space layers and Mixture-of-Experts (MoE) attention, available as a stable preview ahead of the v4.52.0 minor release.