OCGQuant: Outlier-Companion Grouping for NVFP4 Quantization

arXiv:2609.00066 · cs.CL, cs.AI, cs.LG · Submitted 2026-08-30 · Read on arXiv

cs.CL, cs.AI, cs.LG

Submitted: 2026-08-30

Updated: 2026-08-30

Comments: Accepted to EMNLP 2026 (Main Conference)

Code: https://github.com/Eshamont/OCGQuant

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Quantization — 119× in this paper · explained in 12 episodes
• Perplexity — 25× in this paper · explained in 3 episodes
• Calibration — 22× in this paper · explained in 7 episodes
• Accuracy — 21× in this paper · explained in 1 episode
• Outlier-Companion Grouping — 13× in this paper
• Transformer — 5× in this paper · explained in 2 episodes
• KV cache — 4× in this paper · explained in 3 episodes
• Downstream Tasks — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adaptation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Reconstruction Error — 2× in this paper · explained in 2 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Ablation study — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Transfer Learning — 1× in this paper · explained in 10 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• RaZeR: Pushing the Limits of NVFP4 Quantization with Redundant Zero Remapping
• Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
• Training Verifiers to Solve Math Word Problems
• Pretraining Large Language Models with NVFP4
• Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
• LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• The Llama 3 Herd of Models
• Microscaling Data Formats for Deep Learning
• Massive Activations in Large Language Models
• Qwen3 Technical Report
• RPTQ: Reorder-based Post-training Quantization for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering