An in-memory cache with item expiration and generics

Starlark implementation of bazel rules for CUDA.

Lightweight C++ command line option parser

Neural Modules: a toolkit for conversational AI

Sample C++ command-line Riva clients.

The Triton backend for the PyTorch TorchScript models.

Conversational AI Benchmark.

Cloud-native high-performance edge/middle/service proxy

Bazel build files for open-source projects

TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.

C++ code samples for using Google Cloud Platform

Milvus -- the world's fastest vector search engine.

A Python library for the Docker Engine API

Explore the Capabilities of the TensorRT Platform

The TensorRT Inference Server provides a cloud inferencing solution optimized for NVIDIA GPUs.

Toolkit for efficient experimentation with various sequence-to-sequence models

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

This is now the official location of the Kaldi project.

Connectionist Temporal Classification (CTC) decoding algorithms: best path, prefix search, beam search and token passing. Implemented in Python and OpenCL.

PyTorch bindings for Warp-CTC

Speech Recognition using DeepSpeech2 and the CTC activation function. Edit

PyTorch CTC Decoder bindings

Computation using data flow graphs for scalable machine learning

Data loaders and abstractions for text and NLP

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

Tensors and Dynamic neural networks in Python with strong GPU acceleration