Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM
cs.AI
Submitted: 2026-09-03
Updated: 2026-09-03
Terminology
Sources
- QUASAR: Lowering the Loss Floor of Quantization-Aware Training with Loss-Aware Reconstruction
- Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality
- LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
- GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
- RULER: What's the Real Context Size of Your Long-Context Language Models?
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
- Pretraining Large Language Models with NVFP4
- Microscaling Data Formats for Deep Learning
- SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
- Parallelizing Linear Transformers with the Delta Rule over Sequence Length
- Gated Delta Networks: Improving Mamba2 with Delta Rule
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection