Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

sycl: add a batched L2_NORM kernel (#28222)
Titaniumtown committed 2 months ago
dbeb375
ggml: add gfx90c HIP support (#26454)
AuroraRAS committed 2 months ago
4735997
vulkan: support type-aligned GET_ROWS (#28253)
Jeff Bolz committed 2 months ago
0cae430
5202104
b74f590
vulkan: rms_norm fusion opportunities (#28024)
Jeff Bolz committed 2 months ago
9ac8c40
2092353
cuda: fixes races in mmid and mmf (#28475)
Aman Gupta committed 2 months ago
73a43d1
grammar : fix max repetition threshold (#28469)
Aldehir Rojas committed 2 months ago
9e0e220
ui: Improve Chat Messages rendering performance (#28460)
Aleksander Grygier committed 2 months ago
0afb805
common: add --log-jsonl (#28437)
Xuan-Son Nguyen committed 2 months ago
7620399
ui : embed assets directly with CMake (#28445)
Adrien Gallouët committed 2 months ago
c457e3b
971595d
Github: limit blank issues to maintainers (#28435)
Johannes Gäßler committed 2 months ago
74a7c89
metal : fix memory leak in early return (#28399)
Niklas Wenzel committed 2 months ago
6a1a922
427291b