npuichigo

openai_trtllm

OpenAI compatible API for TensorRT LLM triton backend

agrpc

Async GRPC with C++20 coroutine support

exec-rs

C++ p2300 proposal in Rust

blazing-fast-io-tutorial

Blazing fast data loading with HuggingFace Dataset and Ray Data

tarzan

High-level API for tar-based dataset

snake

Data loading with combined async Rust stream and Python

webrtc

asio-grpc

Asynchronous gRPC with Boost.Asio executors

Best-README-Template

An awesome README template to jumpstart your projects!

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

esp-v2

A service proxy that provides API management capabilities using Google Service Infrastructure.

exmpl-cmake-grpc

Example cmake project for grpc / protobuf

io_uring-echo-server

io_uring echo server

istio-stack

Istio+OTel+Tempo+Loki+Promethues

libevent

Event notification library

libunifex

Unified Executors

wg21_p2300_std_execution

`std::execution`, the proposed C++ framework for asynchronous and parallel programming.

Asynchronous-Programming-in-Rust

Asynchronous Programming in Rust, published by Packt

candle

Minimalist ML framework for Rust

charts

Bitnami Helm Charts

clion-remote

conan-center-index

Recipes for the ConanCenter repository

fastapi-jaeger

Trace FastAPI with Jaeger through OpenTelemetry Python API and SDK.

flash-attention

Fast and memory-efficient exact attention

http

Rust HTTP types

jkb_test

langchain

⚡ Building applications with LLMs through composability ⚡

NeMo

NeMo: a toolkit for conversational AI

ray

Ray is a unified framework for scaling AI and Python applications. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

vector-quantize-pytorch

Vector Quantization, in Pytorch