송현오 교수 연구실
The Thirty-Ninth Annual Conference on Neural Information Processing Systems
Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
구분
국외
국가
미국
컨퍼런스명
The Thirty-Ninth Annual Conference on Neural Information Processing Systems
발표 제목
Q-Palette: Fractional-Bit Quantizers Toward Optimal Bit Allocation for Efficient LLM Deployment
기관명
Neural Information Processing Systems
참여 연도
2025
상세 설명
Neural Information Processing Systems