arXiv (All)
open access
Resource-Efficient Speculative Decoding for Long-Context LLM Serving
Speculative decoding reduces sequential Target model calls by verifying multiple tokens from the Draft model in parallel. Yet KV Cache growth limits long-context serving under constrained GPU memory. Offloading KV to CPU memory relieves this pressure. However, existing offloading schemes restore the
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
- KV-Kaizen: Learning Context-Adaptive Cache Compression Choices#1144877
- KV-Kaizen: Learning Context-Adaptive Cache Compression Choices#1122339
- SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs#1143431
- SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUs#1136792
- Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training#975168
Record · ID 1117896
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