arXiv (All)
open access
Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference
Attention is the dominant source of latency during long-context LLM inference, an increasingly popular workload with reasoning models and RAG. We propose Kascade, a training-free sparse attention method that leverages known observations such as 1) post-softmax attention is intrinsically sparse, 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
- Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference#797287
- SparseBalance: Load-Balanced Long Context Training with Dynamic Sparse Attention#14041
- Suboptimal human inference reflects an efficient and flexible information bottleneck#356362
- Softpick: No Attention Sink, No Massive Activations with Rectified Softmax#149268
- Beyond Repeated Sampling: Learning Search Policies for LLM Reasoning#1062590
Record · ID 798701
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