arXiv (All)
open access
HeadWiseKV: Budgeted Per-Head Cache Residency for Hybrid Long-Context Language Models
Long-context inference retains a growing key--value (KV) cache during decoding, which consumes substantial GPU memory and can reduce generation throughput. This bottleneck remains in hybrid language models because their residual global-attention layers can dominate context-dependent cache demand. We
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
- TierKV: Long-Context On-Device LLMs via Predictive Multi-Tier KV Caching#1035140
- GroupKV: Hierarchical KV Cache Management for Long-Context Diffusion LLM Inference#1011307
- Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs#1142160
- Splitting Prompt Prefill from Response Replay for Context-Parallel Long-Context LLM Post-Training#1117845
- Splitting Prompt Prefill from Response Replay for Context-Parallel Long-Context LLM Post-Training#1108735
Record · ID 822437
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