forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 4
Pull requests: Nathanw1014/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
vulkan: parallelize DSV4 Lightning Indexer prefill
documentation
Improvements or additions to documentation
ggml
testing
Vulkan
#3
opened Aug 13, 2026 by
Mushoz
Loading…
Prefill improvements: 119 -> 210 tok/s at 32k depth, sparse FA 8.16 -> 1.10 seconds
documentation
Improvements or additions to documentation
ggml
testing
Vulkan
#2
opened Aug 13, 2026 by
Mushoz
Loading…
feat: add Motif-3 model architecture support
conversion
model
#1
opened Aug 13, 2026 by
ajaxdude
Loading…
ProTip!
Mix and match filters to narrow down what you’re looking for.