Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

server: reject partial media truncation (#24076)
Yufeng He committed 1 month ago
8e16421
vulkan: sparse flash attention for quantized K/V (#29639)
François-Xavier Gsell committed 1 month ago
b3daa07
ci : winget urls must be separate strings (#29978)
Sigbjørn Skjæret committed 1 month ago
e5983d6
ci : fix docker workflow permissions (#29979)
Sigbjørn Skjæret committed 1 month ago
4ca6b76
metal : few-row MMA mat-mul (#29869)
pratiknarola-t committed 1 month ago
a3a1c47
llama: support both embd + raw tokens in batch (#29622)
Xuan-Son Nguyen committed 1 month ago
0bb496d
CUDA: refactor swizzling code (#29612)
Johannes Gäßler committed 1 month ago
2ca15f5
cuda : move neu_padded to where it is used (#29940)
Adrien Gallouët committed 1 month ago
0eb6d9a
ci : windows llvm build requires ninja multi-config (#29959)
Sigbjørn Skjæret committed 1 month ago
2e7c58c
ci : add windows arm64 vulkan release (#29954)
Sigbjørn Skjæret committed 1 month ago
7f2dd88
AGENTS.md : revamp (#29656)
Aman Gupta committed 1 month ago
bf79dbb
ci : set default permissions (#29945)
Sigbjørn Skjæret committed 1 month ago
46847e6
cuda : move blocks_per_col to where it is used (#29939)
Adrien Gallouët committed 1 month ago
2bc5635
CUDA: fix MMQ memory fault if n_expert >> n_ubatch (#29941)
Johannes Gäßler committed 1 month ago
dd26678
vulkan: fix rdna4 mat_vec tuning (#29934)
Ruben Ortlam committed 1 month ago
16c163d
8330e96
6716df6