paper-with-me

홈 › Papers

Panther: Faster and Cheaper Computations with Randomized Numerical Linear Algebra

2026-01-21 · Fahd Seddik, Abdulrahman Elbedewy, Gaser Sami, Mohamed Abdelmoniem, Yahia Zakaria arxiv

Training modern deep learning models is increasingly constrained by GPU memory and compute limits. While Randomized Numerical Linear Algebra (RandNLA) offers proven techniques to compress these models, the lack of a unified, production-grade library prevents widely adopting these methods. We present Panther, a PyTorch-compatible library that consolidates established RandNLA algorithms into a single high-performance framework. Panther engineers efficient, drop-in replacements for standard components including sketched linear layers, 2D convolution, multi-head attention, and randomized matrix decompositions (such as pivoted CholeskyQR). By implementing a custom C++/CUDA backend (pawX), Panther provides an optimized implementation that can run on both CPUs and GPUs. We demonstrate the effectiveness of RandNLA techniques and Panther's ease of adoption. By replacing standard PyTorch linear layers with Panther layers (requiring only a few lines of code) we achieve significant memory savings (up to 75%) on BERT while maintaining comparable loss. Source code is available (MIT License) at https://github.com/FahdSeddik/panther, along with demonstration video at https://youtu.be/7M3RQb4KWxs.

📄 PDF Abstract BibTeX arXiv:2601.15473

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Panther: Illuminate the Sight of Multimodal LLMs with Instruction-Guided Visual Prompts

2024-11-21 · Honglin Li, Yuting Gao, Chenglu Zhu, Jingdong Chen 외

Multimodal large language models (MLLMs) are closing the gap to human visual perception capability rapidly, while, still lag behind on attending to subtle images details or locating small objects precisely, etc. Common s…

Decoder

Randomized Policy Learning for Continuous State and Action MDPs

2020-06-08 · Hiteshi Sharma, Rahul Jain

Deep reinforcement learning methods have achieved state-of-the-art results in a variety of challenging, high-dimensional domains ranging from video games to locomotion. The key to success has been the use of deep neural …

Deep Reinforcement LearningReinforcement Learning (RL)

Multi-fidelity Monte Carlo: a pseudo-marginal approach

2022-10-04 · Diana Cai, Ryan P. Adams

Markov chain Monte Carlo (MCMC) is an established approach for uncertainty quantification and propagation in scientific applications. A key challenge in applying MCMC to scientific domains is computation: the target dens…

Uncertainty Quantification

DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter

2019-10-02 · NeurIPS 2019 12 · Victor Sanh, Lysandre Debut, Julien Chaumond, Thomas Wolf

As Transfer Learning from large-scale pre-trained models becomes more prevalent in Natural Language Processing (NLP), operating these large models in on-the-edge and/or under constrained computational training or inferen…

Hate Speech DetectionKnowledge DistillationLanguage ModelingLanguage Modelling+7

PANTHER: Pathway Augmented Nonnegative Tensor factorization for HighER-order feature learning

2020-12-15 · Yuan Luo, Chengsheng Mao

Genetic pathways usually encode molecular mechanisms that can inform targeted interventions. It is often challenging for existing machine learning approaches to jointly model genetic pathways (higher-order features) and …

BIG-bench Machine LearningInterpretable Machine Learning