TVM Runtime Support

This crate provides an idiomatic Rust API for TVM runtime, see here for more details.

What Does This Crate Offer?

TVM is an end-to-end deep learning compiler which takes high level machine learning models or tensor computations and lowers them into executable code for a variety of heterogenous devices (e.g., CPU, GPU).

This crate provides access to the APIs for manipulating runtime data structures, as well as TVM's cross-language Object system which functions similarly to systems such as COM, enabling cross-language interoperability.

Installations

Please follow TVM installation instructions, export TVM_HOME=/path/to/tvm and add libtvm_runtime to your LD_LIBRARY_PATH.

Example of registering a cross-language closure.

One can use register! macro to expose a Rust closure with arguments which implement TryFrom<ArgValue> and return types which implement Into<RetValue>. Once registered with TVM these functions can be accessed via Python or C++, or any other language which implements the TVM packed function convention see the offcial documentation for more information.

```rust use tvmrt::{ArgValue, RetValue}; use tvmrt::function::{Function, Result, register};

fn sum(x: i64, y: i64, z: i64) -> i64 { x + y + z }

fn main() { register(sum, "mysum".toowned()).unwrap(); let func = Function::get("mysum").unwrap(); let boxedfn: Box Result> = func.into(); let ret = boxedfn(10, 20, 30).unwrap(); asserteq!(ret, 60); } ```