#Triton实现

1 stories · 0 in 7 days · 0 in 30 days

Stories, products and papers tagged "Triton实现", newest first.

Jun 10

PapersSelected12:12

做长上下文语言模型推理优化的团队，Express 能同时提升预填充和解码效率，值得直接集成到现有流水线中。

arXiv cs.LG@Albert Gong et al. (4)Source