5 releases

0.1.1 May 8, 2023
0.1.0-rc4 May 8, 2023
0.1.0-rc3 May 7, 2023
0.1.0-rc1 May 4, 2023

#1015 in Machine learning

Download history 101/week @ 2024-07-21 76/week @ 2024-07-28 75/week @ 2024-08-04 72/week @ 2024-08-11 43/week @ 2024-08-18 93/week @ 2024-08-25 69/week @ 2024-09-01 72/week @ 2024-09-08 56/week @ 2024-09-15 101/week @ 2024-09-22 91/week @ 2024-09-29 80/week @ 2024-10-06 75/week @ 2024-10-13 53/week @ 2024-10-20 60/week @ 2024-10-27 108/week @ 2024-11-03

323 downloads per month
Used in 12 crates (via llm-base)

MIT license

3.5MB
26K SLoC

C 14K SLoC // 0.1% comments C++ 7K SLoC // 0.1% comments Rust 2.5K SLoC // 0.0% comments Python 768 SLoC // 0.3% comments CUDA 544 SLoC // 0.0% comments Shell 138 SLoC // 0.2% comments

ggml is a semi-idiomatic wrapper for the ggml C library.

It exposes a subset of operations (currently used to implement the llm library). Note that it does not expose a fully-idiomatic safe Rust interface; operations that could be potentially unsafe are marked as such.

ggml operates on a computational graph; no values will be computed until Context::graph_compute is executed. All [Tensor]s are nodes in this computational graph, and values cannot be retrieved until computation is completed.

Dependencies