BitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization
cs.LG, cs.AI
Submitted: 2026-05-22
Updated: 2026-09-27
Code: https://github.com/zjiayu064/BitsMoE
Project page: https://dropbox.github.io/hqq_blog
Terminology
Sources
- Qwen Technical Report
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Mixtral of Experts
- DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
- Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
- Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
- Unveiling Super Experts in Mixture-of-Experts Large Language Models
- Qwen3 Technical Report
- Qwen2.5-1M Technical Report
- MoE-I$^2$: Compressing Mixture of Experts Models through Inter-Expert Pruning and Intra-Expert Low-Rank Decomposition
- HellaSwag: Can a Machine Really Finish Your Sentence?
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks