SGLang is a high-performance serving framework for large language models and multimodal models.

SGLang Omni: High-Performance Multi-Stage Pipeline Framework for Omni Models

Apache DataFusion SQL Query Engine

Open Lakehouse Format for Multimodal AI. Convert from Parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, a…

Apache Iceberg

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

Apache Iceberg - Go

Apache Iceberg C++

MoonEP: A Perfectly Balanced Expert Parallelism Library via Dynamic Redundant Experts

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

Apache Iceberg

Community maintained hardware plugin for vLLM on Apple Silicon

Apache DataFusion Comet Spark Accelerator

LLM algorithm practice lab with theory, solutions, and test cases.《大模型算法实战教程》面向大模型入门到进阶的算法实战教程，覆盖原理讲解、答案解析、测试用例与 CUDA/Triton 实战。

Official Rust implementation of Apache Arrow

Apache Pinot (Incubating) - A realtime distributed OLAP datastore

JSON support for DataFusion (unofficial)

Rust object_store crate

The native Rust implementation for Apache Hudi, with C++ & Python API bindings.

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Spark integrations for working with Lance datasets

The C binding to Lance.

Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.

user-defined functions for Variant handling in Datafusion

An extensible, state-of-the-art framework for columnar compression, and the fastest FOSS columnar file format. Formerly at @spiraldb, now an Incubation Stage project at LFAI&Data, part of the Linux…

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

Tile-Based Runtime for Ultra-Low-Latency LLM Inference