Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

docs: Update quantization readme (#24133)
Pedro Cuenca committed 5 months ago
ad1b88c
minor : fix lint issues (#24165)
Georgi Gerganov committed 5 months ago
59917d3
hparams : refactor `hparams.n_layer` (#24060)
Georgi Gerganov committed 5 months ago
7acb4e8
CUDA: enroll mul_mat_vec_q_moe into pdl (#24087)
Oliver Simons committed 5 months ago
2154a0f
ci : build-msys job slimming [no ci] (#24157)
Daniel Bevenius committed 5 months ago
46fa662
7fe2ae4
server : disable on-device spec checkpoints (#24108)
Georgi Gerganov committed 5 months ago
7c158fb
arg: fix double mtp downloads (#24128)
Xuan-Son Nguyen committed 5 months ago
260862b
ui: Fixed packages (#24119)
Aleksander Grygier committed 5 months ago
21444c8
ui: added single line reasoning preview (#23601)
MagicExists committed 5 months ago
5269770
return filter to save memory (#24125)
forforever73 committed 5 months ago
0dbfa66
convert: Fix Gemma 4 Unified conversion (#24118)
Pedro Cuenca committed 5 months ago
e802356
4c51309
agents: refactor, include more guidelines (#24111)
Xuan-Son Nguyen committed 5 months ago
a121232
readme : add status badges (#24104)
Georgi Gerganov committed 5 months ago
6ddc943
65ef50a
metal : reduce rset heartbeat from 500ms -> 5ms (#24074)
Georgi Gerganov committed 5 months ago
3d19986
3c7450c
sycl : Improve SYCL doc (#23025)
Todd Malsbary committed 5 months ago
f478f1b
mtmd: fix Gemma 4 unified FPE (#24088)
Andrei committed 5 months ago
94a220c