Tied Trit-Planes: Constraining PTQTP to a Uniform Nine-Level Quantizer, with a Persistent Folded Format for Disk-Streamed Mixture-of-Experts Serving
Matteo Grella
cs.CL, cs.LG
Submitted: 2026-08-09
Updated: 2026-08-11
Code: https://github.com/matteo-grella/fucina
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- PTQTP: Post-Training Quantization to Trit-Planes for Large Language Models
- DBQ: A Differentiable Branch Quantizer for Lightweight Deep Neural Networks
- LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
- Unifying Uniform and Binary-coding Quantization for Accurate Compression of Large Language Models
- BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models
- ExTernD: Expanded-Rank Ternary Decomposition Ternary LLM PTQ with Accuracy Approaching Any Quantization Level
- Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization
- Mixture of Quantized Experts (MoQE): Complementary Effect of Low-bit Quantization and Robustness
- QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models
- QuantMoE-Bench: Examining Post-Training Quantization for Mixture-of-Experts
- GuidedQuant: Large Language Model Quantization via Exploiting End Loss Guidance
- QuIP#: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
- T-MAC: CPU Renaissance via Table Lookup for Low-Bit LLM Deployment on Edge
- HOBBIT: A Mixed Precision Expert Offloading System for Fast MoE Inference
- Statistically-Lossless Quantization of Large Language Models
- Displacement Is Not Direction: Evaluating Fidelity Metrics for Quantized LLM Deployment
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Accuracy is Not All You Need
- Divergent Token Metrics: Measuring degradation to prune away LLM components -- and optimize quantization
- CAT-Q: Cost-efficient and Accurate Ternary Quantization for LLMs
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