arXiv (All)
open access
PrefixFlow: Training-Time KV Caching for Schedule-Level Prefix Reuse in LLM RL Training
In reinforcement learning (RL) post-training, one prompt fans out into $N$ trajectories, yet standard trainers replay the shared prefix's forward and backward pass $N$ times; in long-context retrieval-augmented generation (RAG) and multimodal workloads, this repetition dominates training compute. Ex
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
- Pretraining Recurrent Networks without Recurrence#259457
- Replay-Gated Neural Execution: Decoupling Persistent Behavioral Specifications from Neural Realizations in Frozen Language Models#1036926
- Calibrate the Decisions That Change the Future: On-Policy Post-Training Quantization for Multimodal Large Language Models#1132029
- TraceRelay: Attention-Aligned Recurrence over Rolling Traces#1249023
- DepTGL: A Parallel Framework for Memory-based TGNN Training with Adaptive Temporal Data Dependency Management#620705
Record · ID 1357179
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