Skip to content

LLM inference in C/C++

C++ ggml

Commits on master

ggml : fix conv 2d dw (#25490)
Georgi Gerganov committed 4 months ago
5c3a586
c15c5c7
683f0c7
llama-bench : init params.offline (#25476)
Adrien Gallouët committed 4 months ago
259f2e2
ccb0c34
64c8b7d
hexagon: add VISION RoPE support (#25216)
Aparna M P committed 4 months ago
f2d1c2f
32e41fa
1ee0939
cli : move to HTTP-based implementation (#24948)
Xuan-Son Nguyen committed 4 months ago
c264f65
Make hip quality check run on all changes (#25403)
Oliver Simons committed 4 months ago
07e012a
ed8c261
llama: refactor fused ops (#24646)
Aman Gupta committed 4 months ago
90e0f5c
ui: Context usage gauge and panel (#25340)
Aleksander Grygier committed 4 months ago
f1161b1
da46e59
metal : add set_rows with src0 f16 (#25434)
fairydreaming committed 4 months ago
0512ef1