Skip to content

Allow serving llama models with tensor parallel#592

Draft
Jackmin801 wants to merge 1 commit intobigscience-workshop:mainfrom
Jackmin801:llama-tp
Draft

Allow serving llama models with tensor parallel#592
Jackmin801 wants to merge 1 commit intobigscience-workshop:mainfrom
Jackmin801:llama-tp

Commits