MXCode: Vector Quantization for MX-Native Inference at Scale
cs.LG
Submitted: 2026-10-30
Updated: 2026-11-06
Code: https://github.com/microsoft/microxcaling
Terminology
Sources
- Is Finer Better? The Limits of Microscaling Formats in Large Language Models
- UE5M3 FP4 Block Scaling for Stable Language Model Pretraining
- Microscaling Data Formats for Deep Learning
- GPTVQ: The Blessing of Dimensionality for LLM Quantization
- Maia 200: A Software Defined Dataflow System for Large-scale AI Acceleration
- Qwen3 Technical Report
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis