Skip to content

llama : add --lazy-experts for MoE models larger than RAM - #26003

Closed
pwilkin wants to merge 1 commit into
ggml-org:masterfrom
pwilkin:lazy-experts-mmap
Closed

llama : add --lazy-experts for MoE models larger than RAM#26003
pwilkin wants to merge 1 commit into
ggml-org:masterfrom
pwilkin:lazy-experts-mmap