Linux kernel source tree

LLM inference in C/C++

brpc is an Industrial-grade RPC framework using C++ Language, which is often used in high performance system such as Search, Storage, Machine learning, Advertisement, Recommendation etc. "brpc" mea…

Fast and memory-efficient exact attention

Development repository for the Triton language and compiler

An Extensible Toolkit for Finetuning and Inference of Large Foundation Models. Large Models for All.

An industrial-grade C++ implementation of RAFT consensus algorithm based on brpc, widely used inside Baidu to build highly-available distributed systems.

A production-grade java implementation of RAFT consensus algorithm.

Fast inference engine for Transformer models

Tile primitives for speedy kernels

BaikalDB, A Distributed HTAP Database.

A full-text search engine supporting massive users, real-time updating, fast fuzzy matching and flexible table splitting.

To describe your PC's Memory Mountain in graph