ResearchTrend.AI
HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression

HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression

Vladimer Khasia
    MQ
ArXiv (abs)PDFHTMLGithub (9★)

Papers citing "HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression"

0 / 0 papers shown

No papers found