llama.cpp
Load all MoE experts during warmup
#11571
Merged

Load all MoE experts during warmup #11571

fairydreaming
sszymczy llama : use all experts during warmup
83a473a0
sszymczy llama : increased max_nodes as large MoE models use massive amounts o…
c8bc6e4f
cpumaxx
jukofyork
ggerganov
fairydreaming
jukofyork
fairydreaming
fairydreaming fairydreaming closed this 181 days ago
jukofyork
sszymczy Merge remote-tracking branch 'upstream/master' into experts-warmup
21213352
fairydreaming fairydreaming reopened this 181 days ago
fairydreaming
sszymczy llama : correct llama_set_warmup() description
334515f6
ggerganov
ggerganov approved these changes on 2025-03-14
fairydreaming fairydreaming merged 8fcb5636 into master 181 days ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone