Highlights
- Pro
Stars
A Datacenter Scale Distributed Inference Serving Framework
An extremely fast Python package and project manager, written in Rust.
Thunder gives you PyTorch models superpowers for training and inference. Unlock out-of-the-box optimizations for performance, memory and parallelism, or roll out your own.
Generate Go client and server boilerplate from OpenAPI 3 specifications
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
🦜🔗 Build context-aware reasoning applications
Simple, safe way to store and distribute tensors
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Starlark implementation of bazel rules for CUDA.
Converts lcov output to Cobertura-compatible XML for CI
Goal: Enable awesome tooling for Bazel users of the C language family.
Standalone implementation of the CUDA-accelerated WFST Decoder available in Riva
Protocol buffers and other common resources.
BS::thread_pool: a fast, lightweight, modern, and easy-to-use C++17 / C++20 / C++23 thread pool library
C++ Requests: Curl for People, a spiritual port of Python Requests.
An efficient C++17 GPU numerical computing library with Python-like syntax
Locally squash commits on a branch without resolving any conflicts (a'la squash and merge)
TinyXML2 is a simple, small, efficient, C++ XML parser that can be easily integrated into other programs.
Generating bash command from natural language https://arxiv.org/abs/1802.08979
A native gRPC client & server implementation with async/await support.
A General-purpose Task-parallel Programming System using Modern C++
a clean C library for processing UTF-8 Unicode data
An efficient implementation of RNN-T Prefix Beam Search in C++/CUDA.