Hugging Face Integrates Nunchaku 4-bit Diffusion into Diffusers Library
SVDQuant-based quantization now runs natively in Diffusers, cutting VRAM requirements from 24GB to 12GB while accelerating inference.
#diffusion
DiScoFormer Unifies Density and Score Estimation in a Single Transformer
Researchers introduce a transformer architecture that estimates both probability density and score functions across distributions without retraining.
Google DeepMind releases DiffusionGemma, a 26B diffusion model 4x faster than autoregressive generation
DiffusionGemma uses parallel text diffusion instead of sequential token generation, achieving 1000+ tokens/sec on H100 GPUs with trade-offs in output quality.
NVIDIA's Nemotron-Labs Diffusion Models Generate Multiple Tokens in Parallel, Bypassing Autoregressive Bottleneck
NVIDIA releases diffusion language models at 3B, 8B, and 14B scales that generate and refine tokens in parallel, offering latency improvements for GPU-constrained inference workloads.