7 papers
Operator Fusion for LLM Inference on the Tensix Architecture
Qingbo Wu, Ke Li, Wenzhu Wang +3
This study addresses on-device inference bottlenecks of Transformer models on Tenstorrent's Tensix architecture and proposes an operator fusion strategy that enhances data locality…
Calibrating Overconfidence Without Sacrificing Confidence: Probe-Conditioned Head Intervention for LLMs
Ke Li, Chongzhe Zhang, Zifan Zeng +3
Large language models often express high confidence in answers that are wrong. Standard calibration remedies typically act globally or at the score level, reducing unwarranted conf…
Multi-Mixer Models: Flexible Sequence Modeling with Shared Representations
Kevin Y. Li, Asher Trockman, Ananda Theertha Suresh +1
Softmax attention is the cornerstone of modern large language models, but its memory scales linearly and compute quadratically with sequence length. Linear recurrent models, such a…
Mamba-3: Improved Sequence Modeling using State Space Principles
Aakash Lahoti, Kevin Y. Li, Berlin Chen +5
Scaling inference-time compute has emerged as an important driver of LLM performance, making inference efficiency a central focus of model design alongside model quality. While the…
Inference Optimal VLMs Need Fewer Visual Tokens and More Parameters
Kevin Y. Li, Sachin Goyal, Joao D. Semedo +1
Vision Language Models (VLMs) have demonstrated strong capabilities across various visual understanding and reasoning tasks, driven by incorporating image representations into the…
Thinking Slow, Fast: Scaling Inference Compute with Distilled Reasoners
Daniele Paliotta, Junxiong Wang, Matteo Pagliardini +6
Recent advancements have demonstrated that the performance of large language models (LLMs) can be significantly enhanced by scaling computational resources at test time. A common s…