arXiv (All)
open access
Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding
Speculative decoding is critical for accelerating LLM inference. However, the speedup is fragile: drafters are typically trained against a narrow distribution for a single target model, and their acceptance rate collapses under workload shifts. This is a striking inversion of modern LLM development,
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
- To Copy or Not to Copy: Controlling Speculative Decoding via Intrinsic Model Signals#1033956
- Mentored Decoding: Faster Inference meets Boosting#1104673
- SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference#1036094
- SpecQuant: Speculative Decoding with Multi-Parent Quantization for Adaptive LLM Inference#1006872
- Acceptance-Aware Draft Model Training for Speculative Decoding#1050335
Record · ID 987097
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