JetFire: Approximate-then-Correct Attention on Hybrid Memory for Long-Context LLM Inference
Open Access
- 14 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 504-518
Abstract
No abstract availableFunding Information
- Ministry of Education, Singapore (MOE-MOET32024-0003)
- Ministry of Education, Singapore (T2EP20224-0038)
- Google (2026 Google Research Award)
This publication has 13 references indexed in Scilit:
- BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache2026
- The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs2026
- Hcattention: Extreme Kv Cache Compression Via Heterogeneous Attention Computing for LlmsSSRN Electronic Journal, 2025
- A2ATS: Retrieval-Based KV Cache Reduction via Windowed Rotary Position Embedding and Query-Aware Vector Quantization2025
- TailorKV: A Hybrid Framework for Long-Context Inference via Tailored KV Cache Optimization2025
- AI and Memory WallIEEE Micro, 2024
- LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding2024
- Efficient Memory Management for Large Language Model Serving with PagedAttention2023
- GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints2023
- FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness2022