Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

CUDA/HIP: Flash Attention tuning (gfx1201) (#28102)
Piotr Wilkin (ilintar) committed 2 months ago
16378d9
ci : key cache to sanitizer matrix (#28708)
Sigbjørn Skjæret committed 2 months ago
451b89b
df03399
6788edb
52d4268
fa67698
c32d1da
e5a8d43
convert : expand Nemotron H conversion fix (#28689)
Kartik Gulia committed 2 months ago
8c322d5
72797e8
4ea6d1b
f1b6fbf
d7e8643
ci: fix sanitizer tests (#28583)
Eve committed 2 months ago
434ddbb
hexagon: rope updates (#28628)
Todor Boinovski committed 2 months ago
6d9c82e
py : lower numpy to 2.2.6 (#28654)
Sigbjørn Skjæret committed 2 months ago
4b98ab8
py : bump numpy to 2.4.6 (#28649)
Sigbjørn Skjæret committed 2 months ago
9cf3bf2
4850c77
d4abd57