arXiv (All)
open access
To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals
Speculative Decoding (SD) has significantly accelerated Large Language Model (LLM) inference, yet existing approaches face a fundamental tradeoff between two drafting strategies: neural drafting and context-based copying. Neural drafts (e.g., EAGLE3) provide robust performance across diverse text se
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training#975168
- Mentored Decoding: Faster Inference meets Boosting#1104673
- Draft-OPD: On-Policy Distillation for Speculative Draft Models#1035509
- Acceptance-Aware Draft Model Training for Speculative Decoding#1050335
- SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference#1036094
Record · ID 1033956
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive