Highlights
Starred repositories
Digger is an open source IaC orchestration tool. Digger allows you to run IaC in your existing CI pipeline ⚡️
Open-source observability for your LLM application, based on OpenTelemetry
Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".
Composio equip's your AI agents & LLMs with 100+ high-quality integrations via function calling
The Classiq Library is the largest collection of quantum algorithms and applications. It is the best way to explore quantum computing software. We welcome community contributions to our Library 🙌
Unified framework for building enterprise RAG pipelines with small, specialized models
WebAssembly binding for llama.cpp - Enabling on-browser LLM inference
Composable building blocks to build Llama Apps
FastMLX is a high performance production ready API to host MLX models.
Resources of our survey paper "Optimizing Edge AI: A Comprehensive Survey on Data, Model, and System Strategies"
This repository provides code for machine learning algorithms for edge devices developed at Microsoft Research India.
Robust recipes to align language models with human and AI preferences
🤖 The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transf…
Use your own AI models on the web
High-resolution models for human tasks.
Efficient Triton Kernels for LLM Training
Create web-based user interfaces with Python. The nice way.
A curated list for Efficient Large Language Models
Enterprise graph machine learning framework for billion-scale graphs for ML scientists and data scientists.
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
A collection of guides and examples for the Gemma open models from Google.
The official implementation of Self-Play Preference Optimization (SPPO)
Vector (and Scalar) Quantization, in Pytorch