Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

docker : bump cuda to 13.4.1 (#29207)
Sigbjørn Skjæret committed 1 month ago
ec91ab5
af91114
tests : remove stale comment (#29140)
Mostafa committed 1 month ago
711f60b
335b21f
json: Fixed json enum handling (#28518)
Silverside committed 1 month ago
26394b4
8034c1d
6ad1af5
68d9053
8aa161b
webgpu : add fused gdn + cpy (#28976)
Masashi Yoshimura committed 1 month ago
932a68e
convert: enable --fuse-qkv for muse-glimmer (#29203)
David Friehs committed 1 month ago
62668d6
CUDA: tune FA for Gemma 4 on Ampere or newer (#29152)
Johannes Gäßler committed 2 months ago
ce8caa6
metal : support arbitrary hc in dsv4_hc_pre (#29169)
Georgi Gerganov committed 2 months ago
a894dae
3d82ef6
CUDA: enable sparse fa for qwen4 (#28770)
Aman Gupta committed 2 months ago
3cf0325
ui: Fix mobile breakpoint + content overflow issues (#29108)
Aleksander Grygier committed 2 months ago
b23efaa
metal: add F16 input to the FWHT (#29094)
bri-prism committed 2 months ago
9a9f939
chat : fix gemma4 required tool grammar (#29115)
Aldehir Rojas committed 2 months ago
f072b10
hexagon: enable I32 GET_ROWS (#29116)
Aparna M P committed 2 months ago
e613ef2