Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

disable rocm cache (#26962)
Sigbjørn Skjæret committed 3 months ago
7a9ff95
cmake : introduce semantic versioning (#26839)
Daniel Bevenius committed 3 months ago
680a9ae
model : disallow integer dflash sliding_window_pattern (#26900)
Sigbjørn Skjæret committed 3 months ago
ece98b8
sync : ggml
Georgi Gerganov committed 3 months ago
af05a42
cmake : add config version support (ggml/1582)
Daniel Bevenius committed 3 months ago
13fd0bb
ui: add read_media tool (#25877)
parabelboi committed 3 months ago
4dd1275
opencl: default FA c8 cluster width to 16 on X1E (#26433)
Hongqiang Wang committed 3 months ago
89e0aa6
tests : update speculative params (#26925)
Georgi Gerganov committed 3 months ago
a4a4c51
vulkan: add TQ2_0 (ternary) support (#25850)
michaeltrabalka-tech committed 3 months ago
a7cd2f0
ci : add missing release check (#26923)
Sigbjørn Skjæret committed 3 months ago
7b13a84
spec : update speculative-simple (#26904)
Georgi Gerganov committed 3 months ago
f785fc9
ba360ef
ci : add windows-rocm to check-release (#26897)
Sigbjørn Skjæret committed 3 months ago
70dfba5
2468576
Dflash support for nemotron-3.5 (#26905)
lnigam committed 3 months ago
cc078b4
mtmd: support pocket-tts (#26871)
Xuan-Son Nguyen committed 3 months ago
6e62ba5
8d274dd