arXiv (All)
open access
Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy
and-cluster-computingartificial-intelligencecomputation-and-languagedistributedmachine-learningparallel
Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only the selected entries, but it uses one cache budget at every load and does not handle draft-model speculative decoding such as DSpark and DFlash2. We p
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
- Adaptive DHiSparse: Speculative Decoding over a Load-Adaptive KV Hierarchy#1291767
- Resource-Efficient Speculative Decoding for Long-Context LLM Serving#1117896
- When Parallel Drafter Meets Parallel Speculative Decoding#1063607
- AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters#1257979
- Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training#975168
Record · ID 1298204
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