LLM inference in C/C++
C++ ggml
Commits on master
chat: fix whitespace problems once and for all (#24624)
a6dff71 Piotr Wilkin (ilintar) committed 5 months ago
ggml-webgpu: improve i-quants mul_mat performance and speed up prefill (#24530)
6e9007a Masashi Yoshimura committed 5 months ago
convert : fix lora base model arch retrieval (#24621)
dd4623a Sigbjørn Skjæret committed 5 months ago
fix(ui): render thinking/reasoning block content as markdown (#24611)
ef8268f franitel committed 5 months ago
chat: add dedicated Cohere2MoE (North Code) parser (#24615)
aedb2a5 Piotr Wilkin (ilintar) committed 5 months ago
docs : fix typos in CUDA-FEDORA.md and grammars/README.md (#24459)
8edaca9 Mohammad Athar committed 5 months ago
docker: specify registry to simplify Podman builds (#24607)
20c5266 Alexander Batischev committed 5 months ago
ui : fix ui clipping in mobile due to incorrect height setup (#24605)
1fd6dfe Amos Wong committed 5 months ago
ui : fix llama-ui-embed crash when no asset dir is given (#24597)
53bd47e Aldehir Rojas committed 5 months ago
jinja : fix negative step slice with start/stop values (#24580)
f05cf46 Sigbjørn Skjæret committed 5 months ago
jinja : fix split and replace with empty first arg (#24574)
341babc Sigbjørn Skjæret committed 5 months ago