arXiv (OAI Expanded)
open access
Shared-Prefix KV Reuse Across Standard LoRA Adapters: Quality and Serving Tradeoffs
A common small-model deployment runs one shared backbone with several LoRA specialists that answer over the same context. Serving them naively re-prefills that shared context once per specialist. We study a narrow, practical question: for already-trained standard LoRA adapters -- not adapters retrai
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
- Shared-Prefix KV Reuse Across Standard LoRA Adapters: Quality and Serving Tradeoffs#919453
- Routing Is Not Enough: Diagnosing Intra-Adapter Subspace Contention in MoE+LoRA Fine-Tuning#925513
- SAIA: a seamless Slurm-native solution for HPC-based services#164226
- Deployment Considerations for Dual-Stack Lite#133451
- Recommendations for Prefix Binding in the Context of Softwire Dual-Stack Lite#502044
Record · ID 1123500
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