
JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Stars: 290

JetStream is a throughput and memory optimized engine for Large Language Model (LLM) inference on XLA devices, specifically TPUs. It provides reference engine implementations for Jax and Pytorch models, along with documentation for online inference, serving Gemma using TPUs on GKE, benchmarking, observability, profiling, and standalone local setup. Users can easily set up a local server, run tests, and test core modules. JetStream aims to enhance the performance of LLM inference on XLA devices.
README:
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).
Currently, there are two reference engine implementations available -- one for Jax models and another for Pytorch models.
- Git: https://github.com/google/maxtext
- README: https://github.com/google/JetStream/blob/main/docs/online-inference-with-maxtext-engine.md
- Git: https://github.com/google/jetstream-pytorch
- README: https://github.com/google/jetstream-pytorch/blob/main/README.md
- Online Inference with MaxText on v5e Cloud TPU VM [README]
- Online Inference with Pytorch on v5e Cloud TPU VM [README]
- Serve Gemma using TPUs on GKE with JetStream
- Benchmark JetStream Server
- Observability in JetStream Server
- Profiling in JetStream Server
- JetStream Standalone Local Setup
make install-deps
Use the following commands to run a server locally:
# Start a server
python -m jetstream.core.implementations.mock.server
# Test local mock server
python -m jetstream.tools.requester
# Load test local mock server
python -m jetstream.tools.load_tester
# Test JetStream core orchestrator
python -m unittest -v jetstream.tests.core.test_orchestrator
# Test JetStream core server library
python -m unittest -v jetstream.tests.core.test_server
# Test mock JetStream engine implementation
python -m unittest -v jetstream.tests.engine.test_mock_engine
# Test mock JetStream token utils
python -m unittest -v jetstream.tests.engine.test_token_utils
python -m unittest -v jetstream.tests.engine.test_utils
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for JetStream
Similar Open Source Tools

JetStream
JetStream is a throughput and memory optimized engine for Large Language Model (LLM) inference on XLA devices, specifically TPUs. It provides reference engine implementations for Jax and Pytorch models, along with documentation for online inference, serving Gemma using TPUs on GKE, benchmarking, observability, profiling, and standalone local setup. Users can easily set up a local server, run tests, and test core modules. JetStream aims to enhance the performance of LLM inference on XLA devices.

JetStream
JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome). It is designed to provide high performance and scalability for large language models, enabling efficient inference on cloud-based TPUs. JetStream leverages XLA to optimize the execution of LLM models, resulting in faster and more efficient inference. Additionally, JetStream supports quantization techniques to further enhance performance and reduce memory consumption. By utilizing JetStream, developers can deploy and run LLM models on TPUs with ease, achieving optimal performance and cost-effectiveness.

mlir-aie
This repository contains an MLIR-based toolchain for AI Engine-enabled devices, such as AMD Ryzen™ AI and Versal™. This repository can be used to generate low-level configurations for the AI Engine portion of these devices. AI Engines are organized as a spatial array of tiles, where each tile contains AI Engine cores and/or memories. The spatial array is connected by stream switches that can be configured to route data between AI Engine tiles scheduled by their programmable Data Movement Accelerators (DMAs). This repository contains MLIR representations, with multiple levels of abstraction, to target AI Engine devices. This enables compilers and developers to program AI Engine cores, as well as describe data movements and array connectivity. A Python API is made available as a convenient interface for generating MLIR design descriptions. Backend code generation is also included, targeting the aie-rt library. This toolchain uses the AI Engine compiler tool which is part of the AMD Vitis™ software installation: these tools require a free license for use from the Product Licensing Site.

AIaW
AIaW is a next-generation LLM client with full functionality, lightweight, and extensible. It supports various basic functions such as streaming transfer, image uploading, and latex formulas. The tool is cross-platform with a responsive interface design. It supports multiple service providers like OpenAI, Anthropic, and Google. Users can modify questions, regenerate in a forked manner, and visualize conversations in a tree structure. Additionally, it offers features like file parsing, video parsing, plugin system, assistant market, local storage with real-time cloud sync, and customizable interface themes. Users can create multiple workspaces, use dynamic prompt word variables, extend plugins, and benefit from detailed design elements like real-time content preview, optimized code pasting, and support for various file types.

moling
MoLing is a computer-use and browser-use MCP Server that implements system interaction through operating system APIs, enabling file system operations such as reading, writing, merging, statistics, and aggregation, as well as the ability to execute system commands. It is a dependency-free local office automation assistant. Requiring no installation of any dependencies, MoLing can be run directly and is compatible with multiple operating systems, including Windows, Linux, and macOS. This eliminates the hassle of dealing with environment conflicts involving Node.js, Python, Docker, and other development environments. Command-line operations are dangerous and should be used with caution. MoLing supports features like file system operations, command-line terminal execution, browser control powered by 'github.com/chromedp/chromedp', and future plans for personal PC data organization, document writing assistance, schedule planning, and life assistant features. MoLing has been tested on macOS but may have issues on other operating systems.

SiLLM
SiLLM is a toolkit that simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework. It provides features such as LLM loading, LoRA training, DPO training, a web app for a seamless chat experience, an API server with OpenAI compatible chat endpoints, and command-line interface (CLI) scripts for chat, server, LoRA fine-tuning, DPO fine-tuning, conversion, and quantization.

OmniSteward
OmniSteward is an AI-powered steward system based on large language models that can interact with users through voice or text to help control smart home devices and computer programs. It supports multi-turn dialogue, tool calling for complex tasks, multiple LLM models, voice recognition, smart home control, computer program management, online information retrieval, command line operations, and file management. The system is highly extensible, allowing users to customize and share their own tools.

Scriberr
Scriberr is a self-hostable AI audio transcription app that utilizes open-source Whisper models from OpenAI for transcribing audio files locally on user's hardware. It offers fast transcription with customizable compute settings, local transcription on device, API endpoints for automation, and integration with other tools. Users can optionally summarize transcripts using ChatGPT or Ollama, with support for custom prompts. The app is mobile-ready, simple, and easy to use, with planned features including speaker diarization, audio recording, file actions, full text fuzzy search, tag-based organization, follow-along text with playback, edit summaries, export options, and support for other languages. Despite being in beta, Scriberr is functional and usable, albeit with some rough edges and minor bugs.

brain4j
Brain4J is a lightweight, performant, and open-source machine learning framework for Java. Designed with portability and speed in mind, it is optimized for high performance and ideal for those looking to implement machine learning solutions in pure Java. The framework provides tools and functionalities to facilitate the development of machine learning models within Java applications, offering ease of use and efficiency.

AIOS
AIOS, a Large Language Model (LLM) Agent operating system, embeds large language model into Operating Systems (OS) as the brain of the OS, enabling an operating system "with soul" -- an important step towards AGI. AIOS is designed to optimize resource allocation, facilitate context switch across agents, enable concurrent execution of agents, provide tool service for agents, maintain access control for agents, and provide a rich set of toolkits for LLM Agent developers.

sdk-python
Strands Agents is a lightweight and flexible SDK that takes a model-driven approach to building and running AI agents. It supports various model providers, offers advanced capabilities like multi-agent systems and streaming support, and comes with built-in MCP server support. Users can easily create tools using Python decorators, integrate MCP servers seamlessly, and leverage multiple model providers for different AI tasks. The SDK is designed to scale from simple conversational assistants to complex autonomous workflows, making it suitable for a wide range of AI development needs.

SciPIP
SciPIP is a scientific paper idea generation tool powered by a large language model (LLM) designed to assist researchers in quickly generating novel research ideas. It conducts a literature review based on user-provided background information and generates fresh ideas for potential studies. The tool is designed to help researchers in various fields by providing a GUI environment for idea generation, supporting NLP, multimodal, and CV fields, and allowing users to interact with the tool through a web app or terminal. SciPIP uses Neo4j as its database and provides functionalities for generating new ideas, fetching papers, and constructing the database.

OpenManus
OpenManus is an open-source project aiming to replicate the capabilities of the Manus AI agent, known for autonomously executing complex tasks like travel planning and stock analysis. The project provides a modular, containerized framework using Docker, Python, and JavaScript, allowing developers to build, deploy, and experiment with a multi-agent AI system. Features include collaborative AI agents, Dockerized environment, task execution support, tool integration, modular design, and community-driven development. Users can interact with OpenManus via CLI, API, or web UI, and the project welcomes contributions to enhance its capabilities.

graphiti
Graphiti is a framework for building and querying temporally-aware knowledge graphs, tailored for AI agents in dynamic environments. It continuously integrates user interactions, structured and unstructured data, and external information into a coherent, queryable graph. The framework supports incremental data updates, efficient retrieval, and precise historical queries without complete graph recomputation, making it suitable for developing interactive, context-aware AI applications.

inspectus
Inspectus is a versatile visualization tool for large language models. It provides multiple views, including Attention Matrix, Query Token Heatmap, Key Token Heatmap, and Dimension Heatmap, to offer insights into language model behaviors. Users can interact with the tool in Jupyter notebooks through an easy-to-use Python API. Inspectus allows users to visualize attention scores between tokens, analyze how tokens focus on each other during processing, and explore the relationships between query and key tokens. The tool supports the visualization of attention maps from Huggingface transformers and custom attention maps, making it a valuable resource for researchers and developers working with language models.

BentoML
BentoML is an open-source model serving library for building performant and scalable AI applications with Python. It comes with everything you need for serving optimization, model packaging, and production deployment.
For similar tasks

JetStream
JetStream is a throughput and memory optimized engine for Large Language Model (LLM) inference on XLA devices, specifically TPUs. It provides reference engine implementations for Jax and Pytorch models, along with documentation for online inference, serving Gemma using TPUs on GKE, benchmarking, observability, profiling, and standalone local setup. Users can easily set up a local server, run tests, and test core modules. JetStream aims to enhance the performance of LLM inference on XLA devices.

commanddash
Dash AI is an open-source coding assistant for Flutter developers. It is designed to not only write code but also run and debug it, allowing it to assist beyond code completion and automate routine tasks. Dash AI is powered by Gemini, integrated with the Dart Analyzer, and specifically tailored for Flutter engineers. The vision for Dash AI is to create a single-command assistant that can automate tedious development tasks, enabling developers to focus on creativity and innovation. It aims to assist with the entire process of engineering a feature for an app, from breaking down the task into steps to generating exploratory tests and iterating on the code until the feature is complete. To achieve this vision, Dash AI is working on providing LLMs with the same access and information that human developers have, including full contextual knowledge, the latest syntax and dependencies data, and the ability to write, run, and debug code. Dash AI welcomes contributions from the community, including feature requests, issue fixes, and participation in discussions. The project is committed to building a coding assistant that empowers all Flutter developers.

ollama4j
Ollama4j is a Java library that serves as a wrapper or binding for the Ollama server. It facilitates communication with the Ollama server and provides models for deployment. The tool requires Java 11 or higher and can be installed locally or via Docker. Users can integrate Ollama4j into Maven projects by adding the specified dependency. The tool offers API specifications and supports various development tasks such as building, running unit tests, and integration tests. Releases are automated through GitHub Actions CI workflow. Areas of improvement include adhering to Java naming conventions, updating deprecated code, implementing logging, using lombok, and enhancing request body creation. Contributions to the project are encouraged, whether reporting bugs, suggesting enhancements, or contributing code.

crewAI-tools
The crewAI Tools repository provides a guide for setting up tools for crewAI agents, enabling the creation of custom tools to enhance AI solutions. Tools play a crucial role in improving agent functionality. The guide explains how to equip agents with a range of tools and how to create new tools. Tools are designed to return strings for generating responses. There are two main methods for creating tools: subclassing BaseTool and using the tool decorator. Contributions to the toolset are encouraged, and the development setup includes steps for installing dependencies, activating the virtual environment, setting up pre-commit hooks, running tests, static type checking, packaging, and local installation. Enhance AI agent capabilities with advanced tooling.

lightning-lab
Lightning Lab is a public template for artificial intelligence and machine learning research projects using Lightning AI's PyTorch Lightning. It provides a structured project layout with modules for command line interface, experiment utilities, Lightning Module and Trainer, data acquisition and preprocessing, model serving APIs, project configurations, training checkpoints, technical documentation, logs, notebooks for data analysis, requirements management, testing, and packaging. The template simplifies the setup of deep learning projects and offers extras for different domains like vision, text, audio, reinforcement learning, and forecasting.

Magic_Words
Magic_Words is a repository containing code for the paper 'What's the Magic Word? A Control Theory of LLM Prompting'. It implements greedy back generation and greedy coordinate gradient (GCG) to find optimal control prompts (magic words). Users can set up a virtual environment, install the package and dependencies, and run example scripts for pointwise control and optimizing prompts for datasets. The repository provides scripts for finding optimal control prompts for question-answer pairs and dataset optimization using the GCG algorithm.

grafana-llm-app
This repository contains separate packages for Grafana LLM Plugin and the @grafana/llm package for interfacing with it. The packages are tightly coupled and developed together with identical dependencies. The repository provides instructions for developing the packages, including backend and frontend development, testing, and release processes.

crewAI-tools
This repository provides a guide for setting up tools for crewAI agents to enhance functionality. It offers steps to equip agents with ready-to-use tools and create custom ones. Tools are expected to return strings for generating responses. Users can create tools by subclassing BaseTool or using the tool decorator. Contributions are welcome to enrich the toolset, and guidelines are provided for contributing. The development setup includes installing dependencies, activating virtual environment, setting up pre-commit hooks, running tests, static type checking, packaging, and local installation. The goal is to empower AI solutions through advanced tooling.
For similar jobs

weave
Weave is a toolkit for developing Generative AI applications, built by Weights & Biases. With Weave, you can log and debug language model inputs, outputs, and traces; build rigorous, apples-to-apples evaluations for language model use cases; and organize all the information generated across the LLM workflow, from experimentation to evaluations to production. Weave aims to bring rigor, best-practices, and composability to the inherently experimental process of developing Generative AI software, without introducing cognitive overhead.

LLMStack
LLMStack is a no-code platform for building generative AI agents, workflows, and chatbots. It allows users to connect their own data, internal tools, and GPT-powered models without any coding experience. LLMStack can be deployed to the cloud or on-premise and can be accessed via HTTP API or triggered from Slack or Discord.

VisionCraft
The VisionCraft API is a free API for using over 100 different AI models. From images to sound.

kaito
Kaito is an operator that automates the AI/ML inference model deployment in a Kubernetes cluster. It manages large model files using container images, avoids tuning deployment parameters to fit GPU hardware by providing preset configurations, auto-provisions GPU nodes based on model requirements, and hosts large model images in the public Microsoft Container Registry (MCR) if the license allows. Using Kaito, the workflow of onboarding large AI inference models in Kubernetes is largely simplified.

PyRIT
PyRIT is an open access automation framework designed to empower security professionals and ML engineers to red team foundation models and their applications. It automates AI Red Teaming tasks to allow operators to focus on more complicated and time-consuming tasks and can also identify security harms such as misuse (e.g., malware generation, jailbreaking), and privacy harms (e.g., identity theft). The goal is to allow researchers to have a baseline of how well their model and entire inference pipeline is doing against different harm categories and to be able to compare that baseline to future iterations of their model. This allows them to have empirical data on how well their model is doing today, and detect any degradation of performance based on future improvements.

tabby
Tabby is a self-hosted AI coding assistant, offering an open-source and on-premises alternative to GitHub Copilot. It boasts several key features: * Self-contained, with no need for a DBMS or cloud service. * OpenAPI interface, easy to integrate with existing infrastructure (e.g Cloud IDE). * Supports consumer-grade GPUs.

spear
SPEAR (Simulator for Photorealistic Embodied AI Research) is a powerful tool for training embodied agents. It features 300 unique virtual indoor environments with 2,566 unique rooms and 17,234 unique objects that can be manipulated individually. Each environment is designed by a professional artist and features detailed geometry, photorealistic materials, and a unique floor plan and object layout. SPEAR is implemented as Unreal Engine assets and provides an OpenAI Gym interface for interacting with the environments via Python.

Magick
Magick is a groundbreaking visual AIDE (Artificial Intelligence Development Environment) for no-code data pipelines and multimodal agents. Magick can connect to other services and comes with nodes and templates well-suited for intelligent agents, chatbots, complex reasoning systems and realistic characters.