Back to papers
June 18, 2026cs.LGcs.AIcs.PF
UltraQuant: 4-bit KV Caching for Context-Heavy Agents
Inesh Chakrabarti, David Limpus, Aditi Ghai Rana, Bowen Bao, Spandan Tiwari, Thiago Crepaldi, Ashish Sirasao
Categories
cs.LG, cs.AI, cs.PF
cs.LG, cs.AI, cs.PF