OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond
Paper • 2605.19660 • Published • 39
Zhang
kongzym
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
OScaR: The Occam's Razor for Extreme KV Cache Quantization in LLMs and Beyond upvoted a paper 17 days ago
Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training upvoted a paper 18 days ago
Model Merging Scaling Laws in Large Language ModelsOrganizations
