Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

50e3e3e
64df918
chat : refactor API (#30210)
Aldehir Rojas committed 1 month ago
8b54361
meta : handle host views (#30217)
Georgi Gerganov committed 1 month ago
e60eff9
5e4878e
86a2835
ci : set run-name for publish release (#30214)
Sigbjørn Skjæret committed 1 month ago
5e1d740
server: use port 9931 by default (#30159)
Xuan-Son Nguyen committed 1 month ago
b42b7e6
ui : add the models manager (#29583)
Aleksander Grygier committed 1 month ago
b013e56
d4d82d6
sycl : Q5_K reorder-layout MMVQ and fused GLU (#29375)
Nicolas Mowen committed 1 month ago
3d65c90
Musa FWHT fix (#30167)
bri-prism committed 1 month ago
de7fa0a
CUDA: improve top-k algorithm selection (#28713)
Pranesh Gonegandla committed 1 month ago
71ad059
model : fix DFlash output head sharing (#30111)
Hrishith Thadicherla committed 1 month ago
a11f57b
CUDA: fix MMQ out-of-bounds reads (#29953)
Johannes Gäßler committed 1 month ago
fc9ce6b
c35b667
ui: apply ui_settings on first visit in router mode (#29668)
Simon Sudarushkin committed 1 month ago
4f92965
c811cb8
033df86