Conference Oral: Kitty: Accurate and Efficient 2-bit KV Cache Quantization with Dynamic Channel-wise Precision Boost
Date:
Delivered an oral presentation on our research paper “Kitty” at the International Conference on Machine Learning and Systems (MLSys 2026). The talk focused on the critical bottlenecks of KV cache in Large Language Model (LLM) inference, introducing an innovative approach that combines low-bit quantization with specialized hardware execution to dramatically reduce memory footprint and unlock massive serving throughput improvements.
- Conference: MLSys 2026
- Session: Research Track Oral Presentation: LLM Serving 3
- Official Link: MLSys 2026 Oral Presentation Page