Optimizing Stable Diffusion for Intel CPUs with NNCF and 🤗 Optimum

Fine-tuning Stable Diffusion models on Intel CPUs

Accelerating Stable Diffusion Inference on Intel CPUs

Using Stable Diffusion with Core ML on Apple Silicon

Swift 🧨Diffusers - Fast Stable Diffusion for Mac

Realizing Native INT8 Compute for Diffusion Transformers on Consumer GPUs: A Fused INT8 GEMM Kernel for Ideogram 4.0

arXiv:2606. 14598v1 Announce Type: new Abstract: Post-training INT8 (W8A8) quantization of diffusion transformers is widely deployed as a speed optimization, yet on consumer Ampere GPUs it is frequently slower than the FP8 and NF4 alternatives it is meant to beat.

Faster Stable Diffusion with Core ML on iPhone, iPad, and Mac

Instruction-tuning Stable Diffusion with InstructPix2Pix

Performance Analysis and Optimization of 3D Generative Diffusion Models across GPU Architectures

arXiv:2606. 19365v1 Announce Type: new Abstract: Diffusion models have become essential for high-fidelity 3D MRI synthesis, yet their deployment remains constrained by substantial GPU resource demands arising from hundreds of U-Net evaluations per sample and a highly heterogeneous kernel behavior.

Format-Aware Fusion for Fast FP4 Pretraining

The paper introduces format‑aware fusion, a method that co‑designs quantization producers with their scale domains and consumer layouts to fully exploit four‑bit floating‑point (FP4) Tensor Cores. Using this approach, the authors pretrain the Llama‑3‑family 8B model on 160 billion tokens, achieving up to 37.9 K tokens/s/GPU—significantly higher than standard bfloat16 or Transformer Engine FP4 baselines. The study demonstrates that FP4 performance depends on the interplay of scaling, operand packing, layout, and execution path, with downstream task rankings diverging from training‑loss rankings.

Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware

Masked diffusion language models (dLLMs) promise faster text generation by denoising multiple tokens simultaneously, yet their real‑world serving behavior has been largely unexamined. Using LLaDA‑8B‑Instruct on a single NVIDIA H200 GPU, the study finds that request difficulty is discretized into 11 step‑count levels, short‑budget benchmarks underestimate serving variance, and only 24% of single‑request time is GPU computation, with batching mainly reducing CPU dispatch overhead. The authors also demonstrate that output quality remains stable across batch sizes and propose a batch‑timeout rule for synchronized batching under Poisson arrivals.

Accelerating PyTorch distributed fine-tuning with Intel technologies

Understanding LoRA Rank Trade-offs in Diffusion Model Fine-Tuning

The study investigates how the rank of Low‑Rank Adaptation (LoRA) affects diffusion model fine‑tuning on CIFAR‑10 using a DDPM U‑Net. Experiments with ranks 2, 4, 8, 16, and 32 show that moderate ranks—particularly rank 4—yield the best FID scores while keeping trainable parameters, runtime, and GPU memory low. Higher ranks offer only marginal improvements at a higher computational cost, suggesting that small‑to‑moderate ranks are efficient defaults for fixed training budgets.