arXiv (All)
open access
Acceptance Is Not Speed: Length Inflation in Training-Free Lossy Speculative Decoding
Speculative decoding typically characterizes speedup by draft tokens accepted per verification round. Lossless verification preserves the target model's output distribution and thus expected completion length, making this metric a meaningful efficiency proxy. Relaxed (lossy) verification accepts tok
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
- When Does Better Acceptance Pay? A Controlled Study of Speculative Decoding#1389939
- TreeSpark: Learning to Draft the Trees You Verify for Speculative Decoding#1355107
- DEdit: Iterative Draft Editing for Speculative Decoding#1143111
- LongSpark: Efficient speculative decoding with a fixed-cost parallel drafter#1132230
- SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection#155233
Record · ID 1388186
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