FastVideo UniServe: Production serving for FastH3 on NVIDIA Blackwell GPUs at 1.8x lower latency and 1.45x higher throughputSeptember 29, 2026FastVideo Team
FastVideo FastH3 Goes Local: 7x Speedup on NVIDIA DGX Spark and Apple SiliconSeptember 2, 2026FastVideo Team
FastVideo FastH3 V1: Open-Weight 4-Step Sparse Distilled Minimax H3 for 14x Speedup on NVIDIA Blackwell GPUAugust 27, 2026FastVideo Team
FastMetal-QAD: Fast Local Video Generation on Apple SiliconAugust 10, 2026Aryan Kumar, Will Lin, Hao Zhang
FastAFD: Open-Source Large-Scale Attention-FFN Disaggregation on Blackwell NVL72July 6, 2026Yichao Fu*, Yuxuan Zhang*, Ruitian Wang, Junda Chen, Hao Zhang
JetSpec: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree DraftingJune 22, 2026Lanxiang Hu, Zhaoxiang Feng, Yulun Wu, Haoran Yuan, Yujie Zhao, Yu-Yang Qian, Bojun Wang, Peng Zhao, Daxin Jiang, Yibo Zhu, Tajana Rosing, Hao Zhang
FastWan-QAD: FastVideo generates a 5-Second Video in 1.8 Seconds on a Single NVIDIA GeForce RTX 5090 via Quantization-Aware DistillationJune 15, 2026FastVideo Team
Open-sourcing FastVideo Dreamverse: Real-Time Vibe Directing with LTX-2 on a single NVIDIA B200 GPUMay 26, 2026FastVideo Team
Attn-QAT: Making 4-Bit Attention Actually WorkApril 8, 2026Peiyuan Zhang*, Matthew Noto*, Wenxuan Tan*, Chengquan Jiang, Will Lin, Wei Zhou, Hao Zhang
