Zhang, H., Xia, C., & Wang, Z. (2025). KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference.
Chicago Style (17th ed.) CitationZhang, Huawei, Chunwei Xia, and Zheng Wang. KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference. 2025.
MLA (9th ed.) CitationZhang, Huawei, et al. KVSwap: Disk-aware KV Cache Offloading for Long-Context On-device Inference. 2025.
Warning: These citations may not always be 100% accurate.