tract-cuda 0.23.8

Tiny, no-nonsense, self contained, TensorFlow and ONNX inference
Documentation 
1
2
3
4
5
6
7
8
9
10
11

mod add_matmul_broadcast;
mod fuse_axis_op;
mod fuse_window_into_gemm;
mod pad_q40_weights;
mod untranspose_matmul_output;

pub use add_matmul_broadcast::add_broadcast_pre_matmul;
pub use fuse_axis_op::{fuse_axis_op, fuse_move_axis};
pub use fuse_window_into_gemm::fuse_window_into_gemm;
pub use pad_q40_weights::pad_q40_weights;
pub use untranspose_matmul_output::untranspose_matmul_output;