Inference Acceleration Collection

◆

◆

◆

◆

🔮Psychic

★★

“TurboDiffusion: 100–200× Acceleration for Video Diffusion Models”

◆

◆

◆

◆

📦Normal

★★

“[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.”

◆

◆

◆

◆

🔮Psychic

★★

“Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model”

◆

◆

◆

◆

📦Normal

★★

“[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.”

◆

◆

◆

◆

🔮Psychic

★

“SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention”

◆

◆

◆

◆

🔮Psychic

★

“Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching”

◆

◆

◆

◆

🔮Psychic

★

“Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference”

◆

◆

◆

◆

🔮Psychic

★

“[NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising”

◆

◆

◆

◆

🔮Psychic

★

“⚡️ A fast and flexible PyTorch inference server that runs locally, on any cloud or AI HW. ”

◆

◆

◆

◆

🔮Psychic

★

“KsanaDiT: High-Performance DiT (Diffusion Transformer) Inference Framework for Video & Image Generation”

◆

◆

◆

◆

🔮Psychic

★

“This is the official repo of "QuickLLaMA: Query-aware Inference Acceleration for Large Language Models"”