ShiftCache: Fast and Exact Indel Effect Prediction by Reusing Shifted Reference Encodings
cs.LG, cs.DC
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/calico/baskerville
Terminology
Sources
- Hydragen: High-Throughput LLM Inference with Shared Prefixes
- Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs
- PatchKV: Efficient KV Cache Recovery for Dynamically Edited LLM Contexts
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