forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 11
Pull requests: Luce-Org/lucebox-ggml
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
perf(cuda): extend Q8_1 activation memo to the MMQ MoE path
CUDA
ggml
#34
opened Jul 5, 2026 by
dusterbloom
•
Draft
feat(ggml-cuda): MoE expert-streaming policy + mechanism + fused Q4 kernels
CUDA
documentation
Improvements or additions to documentation
ggml
testing
#22
opened Jun 26, 2026 by
dusterbloom
•
Draft
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.