6 papers
Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
Wenkai Yang, Shuming Ma, Yankai Lin +1
Recent studies have shown that making a model spend more time thinking through longer Chain of Thoughts (CoTs) enables it to gain significant improvements in complex reasoning task…
BitNet v2: Native 4-bit Activations with Hadamard Transformation for 1-bit LLMs
Hongyu Wang, Shuming Ma, Furu Wei
Efficient deployment of 1-bit Large Language Models (LLMs) is hindered by activation outliers, which complicate quantization to low bit-widths. We introduce BitNet v2, a novel fram…
Scaling Optimal LR Across Token Horizons
Johan Bjorck, Alon Benhaim, Vishrav Chaudhary +2
State-of-the-art LLMs are powered by scaling -- scaling model size, dataset size and cluster size. It is economically infeasible to extensively tune hyperparameter for the largest…
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
Jinheng Wang, Hansong Zhou, Ting Song +7
The advent of 1-bit large language models (LLMs), led by BitNet b1.58, has spurred interest in ternary LLMs. Despite this, research and practical applications focusing on efficient…
Next Block Prediction: Video Generation via Semi-Autoregressive Modeling
Shuhuai Ren, Shuming Ma, Xu Sun +1
Next-Token Prediction (NTP) is a de facto approach for autoregressive (AR) video generation, but it suffers from suboptimal unidirectional dependencies and slow inference speed. In…
BitNet a4.8: 4-bit Activations for 1-bit LLMs
Hongyu Wang, Shuming Ma, Furu Wei
Recent research on the 1-bit Large Language Models (LLMs), such as BitNet b1.58, presents a promising direction for reducing the inference cost of LLMs while maintaining their perf…