SSR: Sparse Segment Reduction for Ternary GEMM Acceleration
cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Code: https://github.com/tensorflow/community
Sources
- Large Language Models on Small Resource-Constrained Systems: Performance Characterization, Analysis and Trade-offs
- Ternary Weight Networks
- Trained Ternary Quantization
- Bitnet.cpp: Efficient Edge Inference for Ternary LLMs
- An Efficient Matrix Multiplication Algorithm for Accelerating Inference in Binary and Ternary Neural Networks
- Learning Recurrent Binary/Ternary Weights
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs
- Fast matrix multiplication for binary and ternary CNNs on ARM CPU
- The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks