RunLLM / aqueduct
Aqueduct is no longer being maintained. Aqueduct allows you to run LLM and ML workloads on any cloud infrastructure.
β519Updated last year
Alternatives and similar repositories for aqueduct:
Users that are interested in aqueduct are comparing it to the libraries listed below
- A portable Pythonic Data Lakehouse powered by Ray that brings exabyte-level scalability and fast, ACID-compliant, change-data-capture to β¦β190Updated this week
- Flow with FlorDB π»β154Updated 2 weeks ago
- Coarse-grained lineage and tracing for machine learning pipelines.β467Updated 2 years ago
- Python client library for Modalβ316Updated this week
- A playground for running duckdb as a stateless query engine over a data lakeβ184Updated last year
- Class notes for the course "Long Term Memory in AI - Vector Search and Databases" COS 597A @ Princeton Fall 2023β317Updated last month
- An open-source ML pipeline development platformβ980Updated last month
- The Runhouse Python client. Distribute and run AI workloads magically in Python, like PyTorch for ML infra.β1,003Updated this week
- β31Updated 2 years ago
- A simple DAG for executing LLM calls and using tools.β40Updated last year
- Serverless HTAP cloud data platform powered by Arrow Γ DuckDB Γ Icebergβ318Updated last year
- Ray-based Apache Beam runnerβ43Updated last year
- Framework for building data agent workflowsβ83Updated 6 months ago
- Distributed SQL Query Engine in Python using Rayβ243Updated 4 months ago
- AI Data Management & Evaluation Platformβ215Updated last year
- π¬ modelstore is a Python library that allows you to version, export, and save a machine learning model to your filesystem or a cloud stoβ¦β383Updated last month
- Tracking Ray Enhancement Proposalsβ48Updated last month
- Move fast from data science prototype to pipeline. Capture, analyze, and transform messy notebooks into data pipelines with just two lineβ¦β666Updated this week
- A stateful serverless platformβ239Updated 2 years ago
- Pixeltable β AI Data infrastructure providing a declarative, incremental approach for multimodal workloads.β154Updated this week
- Synchronicity lets you interoperate with asynchronous Python APIs.β103Updated last week
- Provides for deploying custom ETL containers on AIStore, with subsequent user-defined extraction-transformation-loading in parallel, on tβ¦β16Updated this week
- Structured LLM APIsβ155Updated last year
- New file format for storage of large columnar datasets.β482Updated this week
- Serverless multi-protocol + multi-destination event collection system.β202Updated 2 months ago
- The open source metrics layerβ35Updated this week
- VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of yβ¦β687Updated 9 months ago
- Prompt programming with FMs.β440Updated 6 months ago
- Graphsignal Tracer for Pythonβ201Updated this week
- β‘οΈ A fast and flexible PyTorch inference server that runs locally, on any cloud or AI HW.β135Updated 8 months ago