forked from ggml-org/llama.cpp
-
Notifications
You must be signed in to change notification settings - Fork 0
Pull requests: dillon-blake/llama.cpp
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
S1-24: chunked attention — the kernel-free long-context path
#26
opened Jul 14, 2026 by
dillon-blake
Owner
Loading…
S1-29b: the SSM backward wiring S1-29 never landed
#23
opened Jul 14, 2026 by
dillon-blake
Owner
Loading…
S1-28: GLU_BACK — a VJP for every GLU variant
#22
opened Jul 14, 2026 by
dillon-blake
Owner
Loading…
S1-26: OUT_PROD_ID CPU kernel — the activation half of MUL_MAT_ID's backward
#21
opened Jul 13, 2026 by
dillon-blake
Owner
Loading…
S1-27: OUT_PROD_ID_GRP CPU kernel — the weight half of MUL_MAT_ID's backward
#20
opened Jul 13, 2026 by
dillon-blake
Owner
Loading…
ProTip!
Exclude everything labeled
bug with -label:bug.