Showing 81-100 of 321 projects
This project aims to speed up large language model (LLM) inference and enhance their understanding of key information through prompt and KV-Cache compression.
A Python library for machine learning security, providing tools for adversarial attacks and defenses.
Delivers infrastructure for agentic apps with AI-native proxy and data plane.
A powerful PHP static analysis tool that helps find errors and security vulnerabilities in PHP applications.
Causal inference and uplift modeling library for machine learning applications.
AidLearning is a powerful AIOT development platform that provides a Linux environment with GUI, deep learning, and visual IDE support on Android.
An open-source on-device speech recognition library for Apple Silicon devices, built with Swift and Transformers.
A highly optimized GPU-accelerated library for accelerating deep learning training and inference applications.
Inference and training library for high-quality text-to-speech (TTS) models.
Open-source implementation of AlphaEvolve, a coding agent for iterative code optimization and discovery.
A C/C++ implementation of Stable Diffusion and other diffusion models for image generation and processing.
An open-source platform for managing large language models, datasets, and agents with features similar to Hugging Face.
An open-source anomaly detection library with state-of-the-art algorithms and features like experiment management and edge inference.
A high-performance LLM inference API and Chat UI that integrates DeepSeek R1's CoT reasoning traces with Anthropic Claude models.
A PyTorch implementation of Tacotron 2, a state-of-the-art text-to-speech model, with faster-than-realtime inference.
Superduper is an end-to-end framework for building custom AI applications and agents using Python, PyTorch, and Transformers.
A Python library for serving large language models (LLMs) with high performance, including GPU acceleration and distributed inference.
A curated list of awesome papers and code for optimizing LLM/VLM inference performance
Eko is an agentic framework that helps developers build production-ready AI-powered workflows with natural language interactions.
Mooncake is a serving platform for Kimi, a leading LLM service provided by Moonshot AI, focused on disaggregation, inference, and RDMA.
Get weekly updates on trending AI coding tools and projects.