S, S. G., Prakash, S., & Ravindran, B. (2025). SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression.
Chicago Style (17th ed.) CitationS, Santhosh G., Saurav Prakash, and Balaraman Ravindran. SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression. 2025.
MLA (9th ed.) CitationS, Santhosh G., et al. SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression. 2025.
Warning: These citations may not always be 100% accurate.