Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

app : move licences to llama-app (#23824)
Adrien Gallouët committed 5 months ago
98e480a
241cbd4
mtmd-debug: add color and rainbow mode (#23829)
Xuan-Son Nguyen committed 5 months ago
751ebd1
mtmd: fix gemma 4 projector pre_norm (#23822)
Xuan-Son Nguyen committed 5 months ago
c8914ad
ci : run ui publish on ubuntu-slim (#23818)
Sigbjørn Skjæret committed 5 months ago
3ef2369
2f6c815
ci : releases use Github-hosted builds for the UI (#23823)
Georgi Gerganov committed 5 months ago
445b7ce
app : improve help output (#23805)
Adrien Gallouët committed 5 months ago
479a9a1
mtmd: n_head_kv defaults to n_head (#23782)
Saba Fallah committed 5 months ago
0b56d28
mtmd: fix gemma 4 audio rms norm eps (#23815)
Xuan-Son Nguyen committed 5 months ago
d6be315
dd15579
test-llama-archs: fix table format [no release] (#23810)
Johannes Gäßler committed 5 months ago
d374e71
server: minor tweaks to use more cpp features (#23785)
Funtowicz Morgan committed 5 months ago
0b24686
hexagon: minor refresh for HMX FA and MM (#23796)
Max Krasnyansky committed 5 months ago
a919001
48e7078
chat : add Granite 4.1 chat template (#23518)
Jesus Talavera committed 5 months ago
bb771cb
7c48fb8
91eb8f4
d205df6
docker : add ZenDNN Dockerfile (#23716)
Sachin Sharma committed 5 months ago
e8d2567
perplexity : fix format specifier in LOG_ERR (#23788)
Adrien Gallouët committed 5 months ago
48e7eae
convert : add FP8 to Q8 conversion (#23250)
ynankani committed 5 months ago
c522908