arXiv (All)
open access
SPLASH: Co-Designing Sparse Attention with High-Bandwidth Flash for Efficient Long-Context Inference
The key-value (KV) cache has become the dominant consumer of memory in large language model (LLM) serving systems as context lengths, concurrency, and request lifetimes grow. High-bandwidth memory (HBM) provides the bandwidth attention decode needs but limited capacity, while off-package memory and
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
- Meta-analysis of the divided attention paradigm reveals trade-offs between perceptual and mnemonic processing during episodic memory retrieval#242906
- AudioKV: KV Cache Eviction in Efficient Large Audio Language Models#927279
- Stream-CQSA: Exact Out-of-Memory Recovery for Attention#821843
- PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention#1118819
- A Replication of the Impact of Digital Distractions and Semantic Associations on Short-Term Memory Recall#209775
Record · ID 1050008
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