llama.cpp
mtp nextn offload
#26177
Merged

mtp nextn offload #26177

John-194
John-194 fit : count nextn (MTP) blocks in n_gpu_layers so front layers stay o…
093a5377
John-194 John-194 requested a review from JohannesGaessler JohannesGaessler 10 days ago
am17an
am17an approved these changes on 2026-07-27
am17an am17an added merge ready
ggerganov ggerganov merged 0324696b into master 10 days ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone