Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

docs : Eagle3 qwen3 draft model support (#24977)
Kashif Rasul committed 4 months ago
e8ecce5
app : add the llama download subcommand (#24982)
Adrien Gallouët committed 4 months ago
683b04c
fdbd6ab
build: include libmtmd in Apple XCFramework (#21935)
Abraham Gonzalez committed 4 months ago
e12a012
quant : fix quantizing moe with mtp (#24986)
Sigbjørn Skjæret committed 4 months ago
b3ce5ce
sycl : support --split-mode tensor (#24152)
David Spruill committed 4 months ago
e9fb3b3
9c10954
fdb2c11
chat: harden caps check (#24973)
Piotr Wilkin (ilintar) committed 4 months ago
09cedfd
894bb27
common: remove unused json-partial (#24968)
Xuan-Son Nguyen committed 4 months ago
fb40104
1191758
00139b6
ef9c13d
be4a6a6
vulkan: Support GET_ROWS_BACK (#24883)
Jeff Bolz committed 5 months ago
92e854a
vulkan: support CONV_3D (#24612)
Jeff Bolz committed 5 months ago
c560636
0eb874d
server: fix remote preset handling, add test (#24938)
Xuan-Son Nguyen committed 5 months ago
75ad0b2
model: Granite Speech Plus (#24818)
Gabe Goodhart committed 5 months ago
a3900a6
codeowners: add yomaytk to ggml-webgpu (#24930)
Masashi Yoshimura committed 5 months ago
035cd8f