Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

b96806d
3466812
dfc29b6
models : appropriately flag noscan ssm_a tensors (#28121)
Sigbjørn Skjæret committed 2 months ago
f28493c
model : fix gemma4-assistant (#28183)
Sigbjørn Skjæret committed 2 months ago
73159c3
model : load relevant arrays with n_layer_all (#28173)
Sigbjørn Skjæret committed 2 months ago
d11b3cc
metal : add fa-vec tuning for M2 Pro (#28122)
Lukasz Stolcman committed 2 months ago
8887a48
be789c3
9d81721
fe2120b
metal : add fa-vec tuning for M2 Max (#28015)
Georgi Gerganov committed 2 months ago
d08c787
tests : fix log verbosity for test-llama-archs (#28147)
Georgi Gerganov committed 2 months ago
d086dbb
1b89a43
metal: enable Metal 4.0 tensor API on M5+/A19+ (#27461)
James Francis committed 2 months ago
d5d993a
ci: Bump ggml-org/ccache-action to v1.2.24 (#28083)
Ludovic Henry committed 2 months ago
234a6eb
kleidiai : Update KleidiAI Documentation (#26078)
Jonathan Clohessy committed 2 months ago
518b762
0eadefe
09412af
metal : add fa-vec tunings for M1 Ultra (#28088)
Buğra Özgürsoy committed 2 months ago
458681e
e4b9af0
metal : add concat support for quantized types (#28116)
Georgi Gerganov committed 2 months ago
ab0b3bd