Search Results for "masmt runtime engine" - Page 2

Ante is a self-contained terminal coding agent written in Rust and designed to work with many AI models rather than one vendor. It ships as a roughly 15 MB binary with no external runtime dependencies. Users can work through an interactive terminal interface, headless commands, a server protocol, or Slack and Discord gateways. A built-in inference engine can run GGUF models entirely offline without an account, API key, or internet connection. Ante also supports more than a dozen hosted providers and can switch between commercial, open-weight, and local models. ...

Coze Loop is a developer-oriented platform that provides full lifecycle management for AI agents, covering everything from prompt engineering to production monitoring. The project aims to simplify the increasingly complex workflow of building reliable AI agents by offering integrated tools for debugging, evaluation, observability, and optimization. Through its visual playground, developers can test prompts interactively and compare outputs across different language models. The platform also...

Luminal is a framework designed to accelerate and simplify the development of systems-level data applications by using a typed, functional, and streaming-first approach. Instead of treating data processing as a series of ad-hoc scripts, Luminal models transformations as strongly typed building blocks that can be composed into reliable, scalable pipelines. The project emphasizes correctness and performance by requiring explicit types for the data flowing through transformations, reducing...

Llama 2 Everywhere (L2E) is an open-source implementation of the LLaMA-2 large language model architecture designed to demonstrate how transformer-based language models can be executed with extremely minimal code. The project focuses on simplicity and educational clarity by implementing inference for LLaMA-style models in a compact C program rather than relying on large machine learning frameworks. Developers can train models using a Python training pipeline and then run inference using a...

Seldon Server is a machine learning platform and recommendation engine built on Kubernetes. Seldon reduces time-to-value so models can get to work faster. Scale with confidence and minimize risk through interpretable results and transparent model performance. Seldon Core focuses purely on deploying a wide range of ML models on Kubernetes, allowing complex runtime serving graphs to be managed in production.