Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

cuda: unblock mmq for MoE on sm_60 (#26264)
David Friehs committed 2 months ago
fc35562
ci : make cache bucket public (#27728)
Sigbjørn Skjæret committed 2 months ago
da9b5d6
conversion : fix Nemotron 3.5 Lightning layers (#27729)
Daniel Bevenius committed 2 months ago
dac869b
kleidiai: Rework KleidiAI Build System/Integration (#26077)
Jonathan Clohessy committed 2 months ago
d222767
ci : update OS used for ROCM to Ubuntu 24.04 (#27681)
Mario Limonciello committed 2 months ago
eab8ee4
b114b47
0a5ac49
chat : scope qwen3-coder workarounds (#27679)
Aldehir Rojas committed 2 months ago
0cc5b14
790b571
ui: ESLint config updates (#27700)
Aleksander Grygier committed 2 months ago
f1357e4
metal : null-check buffer alloc to fix OOM crash (#25371)
Yuri Khrustalev committed 2 months ago
3737e41
llama.cpp : bump version to 0.3.0 (#27696)
Georgi Gerganov committed 2 months ago
c1d0e7a
sync : ggml
Georgi Gerganov committed 2 months ago
81191af
ggml : bump version to 0.22.0 (ggml/1607)
Georgi Gerganov committed 2 months ago
9388236
sycl : mark tq2_0 as not supported (#27660)
Neo Zhang committed 2 months ago
814d84b
b615f5b
tests : disable DOTS3NOTE arch test for WebGPU (#27654)
fairydreaming committed 2 months ago
7584430
convert: fix GLM regression in index_tensors (#27655)
jacekpoplawski committed 2 months ago
71cc86f
a14dba6
mtmd: video: fix moov atom at the end of file (#27596)
Xuan-Son Nguyen committed 2 months ago
160c6b0
ggml : fix ggml_clamp (#27644)
Georgi Gerganov committed 2 months ago
6036c63