ResearchTrend.AI
BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache

BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache

Dayou Du
Shijie Cao
Jianyi Cheng
Ting Cao
M. Yang
    MQ
ArXivPDFHTML

Papers citing "BitDecoding: Unlocking Tensor Cores for Long-Context LLMs Decoding with Low-Bit KV Cache"

Title
No papers