arXiv (All)
open access
AMEND: Audited Margins Enable Nonblocking Drops in GPU-PIM LLM Decoding
Autoregressive large language model (LLM) decoding re-reads a growing key-value (KV) cache at every step, so long-context attention is bound by graphics processing unit (GPU) memory bandwidth. Block-sparse attention skips low-contribution KV blocks, but a selector that decides after the current quer
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
- NOSA: Native and Offloadable Sparse Attention#1129124
- Dissecting GPU Utilization for LLM Inference on Nvidia Hopper#1070372
- Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation#785132
- Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation#783542
- Bespoke-Card: Why Tune When You Can Generate? Synthesizing Workload-Specific Cardinality Estimators#267750
Record · ID 996642
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