ResServe: Accurate and Efficient FP4 LLM Inference with Residue Compensation
cs.DC
Submitted: 2026-11-05
Updated: 2026-11-05
Code: https://github.com/ShawRong/resserve
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Four Over Six: More Accurate NVFP4 Quantization with Adaptive Block Scaling
- Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
- Pretraining Large Language Models with NVFP4
- Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in $\{\pm 1, \pm i\}$
- Qwen3 Technical Report
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends