Flide: Accelerating Decision Inference with Exact State Forking
cs.CL
Submitted: 2026-10-30
Updated: 2026-10-30
Code: https://github.com/OmniJev/flide
Project page: https://flide.org
Terminology
Sources
- Narrow Decision Models: A System-1 Architecture for Calibrated, Typed Decisions
- Verdict: Encode Once, Decide Many
- PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications
- Gemma 4 Technical Report
- TreeWY: Speculative Verification for Gated DeltaNet Hybrids
- Mamba: Linear-Time Sequence Modeling with Selective State Spaces
- Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the Transcript
- RadixFlow: Filling Execution Bubbles in Prefix-Cached Hybrid LLM Serving
- Hydragen: High-Throughput LLM Inference with Shared Prefixes
- FastJEV: Understanding Redundancy for Compact JEV Inference
- LumoTree: Path-Parallel Speculative Verification for Hybrid Language Models
- RouteLLM: Learning to Route LLMs with Preference Data
- Same Request, Different Answer: Quantization Amplifies Cache-Induced Divergence in LLM Serving
- Sparse Prefix Caching for Hybrid and Recurrent LLM Serving
- BatchLLM: Optimizing Large Batched LLM Inference with Global Prefix Sharing and Throughput-oriented Token Batching
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data