General matrix multiplication of f32 and f64 matrices in Rust. Supports matrices with general strides.
This is a first shot at implementing `gemm` using `i8` as input, and `i16` as output. The main change is to the gemm loops, which are now able to have different types as input and output. # Todo: + [ ] Adapt integration tests for `i8gemm`; + [ ] Fix the masked buffers to work with different kernel dimensions;
This issue appears to be discussing a feature request or bug report related to the repository. Based on the content, it seems to be still under discussion. The issue was opened by SuperFluffy and has received 9 comments.