EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Item #:

085713-4562

Details

DOI: https://doi.org/10.52202/085713-4562
Author(s): Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
Pages: 151568-151587 (20 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)

DOI: https://doi.org/10.52202/085713-4562
Author(s): Yuhui Li, Fangyun Wei, Chao Zhang, Hongyang Zhang
Pages: 151568-151587 (20 pages)
Format: PDF Paper Download
Conference: Advances in Neural Information Processing Systems 38
Date/Location: Held 2-7 December 2025, San Diego, California, USA and 30 November - 5 December 2025, Mexico City, Mexico.
Series: Advances in Neural Information Processing Systems 38
Publisher: Neural Information Processing Systems Foundation, Inc. (NeurIPS)