tensorrt-rs
tensorrt-rs copied to clipboard
mstallmo
Rust library for running TensorRT accelerated deep learning models
batch size made available in the execute function. It is an Option. When giving None, ti defaults to 1.
Hello, as I've seen [here](https://github.com/mstallmo/tensorrt-rs/blob/15475c1fdec1686933ba62213e84676a43656915/tensorrt/src/utils.rs#L10) Error now is `anyhow::Error`. As [description](https://crates.io/crates/anyhow) at crates.io of it suggest: > This library provides anyhow::Error, a trait object based error type for easy idiomatic...
TensorRT engines support two execution modes, sync and async. Sync is already supported and doesn't require any CUDA Streams to run. For async to be supported we need to have...
Issue tracking the completion of bindings to the `nvinfer1::INetworkDefinition` interface in the TesnorRT library. All public functions available from the C++ library should have corresponding Rust bindings.
Issue tracking the completion of bindings to the `nvinfer1::IHostMemory` interface in the TensorRT library. All public functions that are available in the C++ library should have corresponding Rust bindings.
Issue tracking the completion of bindings to the `nvinfer1::IUffParser` interface in TensorRT. All public functions that are available in the C++ library should have corresponding Rust bindings.
We're going to need some good documentation for library examples and usage that will be published on docs.rs once we publish the crate to crates.io. We will also need to...
The current API for creating a Builder, Network, and Parser is very similar to the C++ API provided by TensorRT. This isn't exactly a bad thing but using it in...