Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

cuda: add F16 input to the FWHT (#29096)
bri-prism committed 1 month ago
6f856c7
server : fix wake_fd warning on Windows (#29479)
Adrien Gallouët committed 1 month ago
fcb3074
jinja : implement sameas test (#29448)
Sigbjørn Skjæret committed 1 month ago
81bc6b8
jinja : fix compile error (#29468)
Sigbjørn Skjæret committed 1 month ago
86a24a1
jinja : support noncall test statements with arg (#29443)
Sigbjørn Skjæret committed 1 month ago
a1de614
polished Readme and llama-bench (#28968)
Vladislav committed 1 month ago
965f897
d834d44
9f70b2c
vendor : update cpp-httplib to 0.58.0 (#29407)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 1 month ago
171e884
4b1a27f
mtmd: fix mel preprocessor in LFM2 audio (#29403)
Yuri Khrustalev committed 1 month ago
fcc8915
b248f4a
27b20ba
e351231
5a75f14
[SYCL] support sparse FA (#28796)
Neo Zhang committed 1 month ago
cd74ef6
1ab7e5a