Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

metal : fix im2col 1D case (audio models) (#24220)
Xuan-Son Nguyen committed 5 months ago
daf6bc9
9e3b928
8a963fc
kv-cache : avoid kv cells copies (#24277)
Georgi Gerganov committed 5 months ago
379ac66
llama : add Gemma4 MTP (#23398)
Aman Gupta committed 5 months ago
04eb4c4
spec : fix vocab compatibility check (#24256)
Sigbjørn Skjæret committed 5 months ago
8a091c4
convert : fix Gemma4 with no audio encoder (#24242)
Sigbjørn Skjæret committed 5 months ago
f71af35
docker : bump cuda13 to 13.3.0 (#24228)
Sigbjørn Skjæret committed 5 months ago
3f7c79d
31e8249
completion : remove useless statics (#24226)
Adrien Gallouët committed 5 months ago
6b80c74
completion : fix format specifier in LOG_INF (#24213)
Adrien Gallouët committed 5 months ago
588f0dc
model : rename local n_layer_all variable (#24209)
Sigbjørn Skjæret committed 5 months ago
5343f45
context : fix off-by-one comparisons to n_gpu_layers (#24208)
Sigbjørn Skjæret committed 5 months ago
603300b
da87e9b
model: fix build failed (#24193)
Xuan-Son Nguyen committed 5 months ago
c4a278d
model, mtmd: Granite4 Vision (#23545)
Gabe Goodhart committed 5 months ago
64086f2
TP: round up granularity to 128 (#24180)
Johannes Gäßler committed 5 months ago
6effcec
cli: fix model params not propagated (#23893)
therealkenc committed 5 months ago
86591c7
model : fix llama_model::n_gpu_layers() (#24188)
Georgi Gerganov committed 5 months ago
96fbe00
Fix link to available UI settings (#24169)
Mario committed 5 months ago
9c955c4
ui: add ignore-scripts=true to npmrc (#24149)
Xuan-Son Nguyen committed 5 months ago
cc7bef3