Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

metal : use bf16 math for mxfp4 mul-mat (#29770)
Georgi Gerganov committed 1 month ago
2232bc8
llama-bench : fix docs (#29464)
Marlon Paz committed 1 month ago
79625e0
docs : refresh CPU ops support matrix (#29666)
CaramelizedCUDA committed 1 month ago
66bcc27
model : re-enable -sm tensor for qwen4exp (#28569)
Kevin Hopper committed 1 month ago
10f340d
webgpu: fix SSM_SCAN binding aliasing (#29750)
Masashi Yoshimura committed 1 month ago
0c1e570
ggml-opencl : replace alloca() with std::vector (#29765)
Adrien Gallouët committed 1 month ago
f7b384c
args: fix cli download mmproj arg (#28977)
pr3pony committed 1 month ago
feb9a3d
llama: properly handle KV on training (#28520)
Xuan-Son Nguyen committed 1 month ago
81ff93e
60e9cf7
ggml/gguf : fix integer overflow (#29384)
Daniel Kuts committed 1 month ago
2149c00
codeowners : remove former ZenDNN owner (#29747)
Vishal Singh committed 1 month ago
876c75b
22bdcc4
jinja : support coerced array attributes (#29574)
Sigbjørn Skjæret committed 1 month ago
ca2e203
ggml-et : remove useless alloca() (#29663)
Adrien Gallouët committed 1 month ago
bdeb855