Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

37a215c
4df29be
model : remove some ggml_concat (#27176)
fairydreaming committed 3 months ago
3cb7ffb
10bf611
model: add Kimi-K3 text model (#26185)
Piotr Wilkin (ilintar) committed 3 months ago
ad1de39
server: re-design yield_to_queue thread model (#27133)
Xuan-Son Nguyen committed 3 months ago
22b8e31
vendor: update BoringSSL to 0.20260813.0 (#27099)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 3 months ago
adb55e5
vendor : update cpp-httplib to 0.53.1 (#27103)
Alessandro de Oliveira Faria (A.K.A.CABELO) committed 3 months ago
77140d2
fix: check gguf array type before reading (#27075)
Xuan-Son Nguyen committed 3 months ago
27df919
fixed indent
Masato Nakasaka committed 3 months ago
6b4344e
Fixed gating logic for problematic Intel driver version
Masato Nakasaka committed 3 months ago
7b38cb7
9d57ce4
mtmd, common: various fixes (#27071)
Xuan-Son Nguyen committed 3 months ago
6fed9f6
chat : pass reasoning_effort to template
Andy Williams committed 3 months ago
7e4c0a9
sync : ggml
Georgi Gerganov committed 3 months ago
9b05354
ggml : bump version to 0.20.0 (ggml/1584)
Georgi Gerganov committed 3 months ago
06ae232
llama : allow virtual igpu devices (#26953)
Georgi Gerganov committed 3 months ago
4c1a0af
ggml: force single thread on wasi (#25686)
Mendy Berger committed 3 months ago
c6f6a92