Use PEFT or Full-parameter to finetune 400+ LLMs (Qwen2.5, Llama3.2, GLM4, Internlm2.5, Yi1.5, Mistral, Baichuan2, DeepSeek, ...) or 100+ MLLMs (Qwen2-VL, Qwen2-Audio, Llama3.2-Vision, Llava, Inter…

Assembler for NVIDIA Volta and Turing GPUs

Code, exercises, answers, and hints to go along with the book "Functional Programming in Scala"

Modern concurrency for C++. Tasks, executors, timers and C++20 coroutines to rule them all

Gluten is a middle layer responsible for offloading JVM-based SQL engines' execution to native engines.

mimalloc is a compact general purpose allocator with excellent performance.

Tensor library for machine learning

a fast cross platform AI inference engine 🤖 using Rust 🦀 and WebGPU 🎮

Storage Performance Development Kit

Inferflow is an efficient and highly configurable inference engine for large language models (LLMs).

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Neon: Serverless Postgres. We separated storage and compute to offer autoscaling, code-like database branching, and scale to zero.

未名 BBS 第三方安卓客户端 OBViewer

Graph Library for Approximate Similarity Search

Benchmarks of approximate nearest neighbor libraries in Python

system call hook for Linux

TOD: GPU-accelerated Outlier Detection via Tensor Operations

eBPF-based Networking, Security, and Observability

OSS-Fuzz - continuous fuzzing for open source software.

ModelScope: bring the notion of Model-as-a-Service to life.

✈️The commend client of ssr based Python3

A composable and fully extensible C++ execution engine library for data management systems.

Elastic ephemeral storage

A high-throughput and memory-efficient inference and serving engine for LLMs

MooseFS Distributed Storage – Open Source, Petabyte, Fault-Tolerant, Highly Performing, Scalable Network Distributed File System / Software-Defined Storage

JuiceFS is a distributed POSIX file system built on top of Redis and S3.

LLM inference in C/C++

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.