arXiv (All)
open access
Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training
Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-training. Online co-training can further increase the draft's accuracy, yielding greater speedups. However, scaling this approach to co-training on large models with long contexts poses
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
- Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training#667998
- Resource-Efficient Speculative Decoding for Long-Context LLM Serving#1117896
- Where Does Staleness Accumulate? Pool Aware Effective Staleness Control for Asynchronous RL in LLM Post-Training#1132031
- Osprey: Target-agnostic Pre-training Makes Stronger Drafters in Speculative Decoding#987097
Record · ID 975168
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