Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

mtmd : lfm2 tiles and layout match transformers (#30261)
Yuri Khrustalev committed 1 month ago
4a45de4
model : add H2O-Lightning-4B decision model (#30361)
PSEUDOTENSOR / Jonathan McKinney committed 1 month ago
7e3eeee
mtmd: fix gemma 4 ffn act (#30882)
Xuan-Son Nguyen committed 1 month ago
5ba3b9f
ggml-cuda : support ssm_conv kernel size 7 (#30873)
Tarek Dakhran committed 1 month ago
39da130
36140db
metal : optimize argmax and pool_1d (#30862)
Georgi Gerganov committed 1 month ago
df11702
ci : remove superfluous webgpu jobs (#30868)
Sigbjørn Skjæret committed 1 month ago
b38960f
8115b4c
ggml-cpu : select the NEON fp32->fp16 conversion (#30505)
Bernard Ladenthin committed 1 month ago
119f68d
ggml-zdnn: introduce flash attention op (#30512)
Aaron Teo committed 1 month ago
522f2b6
spec : save the dynamic ngram cache file (#22055)
Peter Sideris committed 1 month ago
83c2d01
13786fb
ci: Fix --strict mode for API check (#30623)
Christian Kastner committed 1 month ago
707616f
1d88cb0
3bb63cb
ci, docs: add WASI CI and docs (#30754)
Mendy Berger committed 1 month ago
921257f