viirya

Modern columnar data format for ML implemented in Rust. Convert from parquet in 2 lines of code for 100x faster random access, vector index, and data versioning. Compatible with Pandas, DuckDB, Polars, Pyarrow, with more integrations coming..

Language:RustApache-2.0010

lancedb

Developer-friendly, serverless vector database for AI applications. Easily add long-term memory to your LLM apps!

Language:PythonApache-2.0000

llama-rs

Run LLaMA inference on CPU, with Rust 🦀🚀🦙

Language:RustApache-2.0010

llama2.rs

A fast llama2 decoder in pure Rust.

Language:RustMIT000

lst-bench

LST-Bench is a framework that allows users to run benchmarks specifically designed for evaluating Log-Structured Tables (LSTs) such as Delta Lake, Apache Hudi, and Apache Iceberg.

Language:JavaApache-2.0010

materialize

Materialize is a fast, distributed SQL database built on streaming internals.

Language:RustNOASSERTION010

mlx-examples

Examples in the MLX framework

Language:PythonMIT010

pyspark-ai

English SDK for Apache Spark

Language:PythonApache-2.0010

qdrant

Qdrant - Vector Database for the next generation of AI applications. Also available in the cloud https://cloud.qdrant.io/

Apache-2.0000

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.

Language:PythonApache-2.0010