# SPLASH: Co-Designing Sparse Attention with High-Bandwidth Flash for Efficient Long-Context Inference

arXiv: https://arxiv.org/abs/2609.23816 · HTML: https://mlsanity.com/paper/2609.23816/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 53 of its 92 references that are in the map.
- First posted on arXiv 20 Sep 2026.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 30 of 53)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference](https://mlsanity.com/paper/2406.10774/) (2024)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention](https://mlsanity.com/paper/2502.11089/) (2025)
- [∞Bench: Extending Long Context Evaluation Beyond 100K Tokens](https://mlsanity.com/paper/2402.13718/) (2024)
- [DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models](https://mlsanity.com/paper/2309.14509/) (2023)
- [InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management](https://mlsanity.com/paper/2406.19707/) (2024)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [L-Eval: Instituting Standardized Evaluation for Long Context Language Models](https://mlsanity.com/paper/2307.11088/) (2023)
- [InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory](https://mlsanity.com/paper/2402.04617/) (2024)
- [Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention](https://mlsanity.com/paper/2403.19708/) (2024)
- [LM-Infinite: Zero-Shot Extreme Length Generalization for Large Language Models](https://mlsanity.com/paper/2308.16137/) (2023)
- [Vidur: A Large-Scale Simulation Framework For LLM Inference](https://mlsanity.com/paper/2405.05465/) (2024)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [AI and Memory Wall](https://mlsanity.com/paper/2403.14123/) (2024)
- [BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems](https://mlsanity.com/paper/2401.17644/) (2024)

## Abstract (arXiv)

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 storage add capacity but lack the bandwidth to sustain attention decode. High-Bandwidth Flash (HBF) is a promising substrate that combines terabyte-scale capacity with near-HBM read bandwidth. Limited write endurance makes read-only model weights its natural use, but we argue that HBF paired with HBM as a hierarchy can also hold the KV cache. Unlike prior hierarchies, whose secondary tiers are bandwidth bottlenecked, the comparable bandwidths let the two act as one logical memory for the long-context KV cache. HBF capacity enables long-context serving, and sparse attention makes it efficient by limiting KV-cache reads during memory-bound decode. Since HBF reads full flash pages and aggregates bandwidth by accessing thousands of parallel flash planes, sparse attention must be co-designed with these physical properties. We present SPLASH, an algorithm and architecture co-design that virtualizes the KV cache across HBM and HBF and adapts sparse attention to HBF's page granularity and plane-level parallelism. Across models and context lengths, SPLASH improves decode throughput per GPU by 3.5x-11.4x over the evaluated baselines under a 100 ms per-token latency objective, while keeping accuracy within 4% of dense attention across long-context suites.