Intel confidential computing - TDX

🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.

Perforator is a cluster-wide continuous profiling tool designed for large data centers

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…

LLaDA is a diffusion model for natural language that, unlike traditional autoregressive models, learns to model the distribution of text through a process of progressive data masking and its invers…

Noise supression using deep filtering

Free and Open Source Machine Translation API. Self-hosted, offline capable and easy to setup.

Core Engine of Singing Voice Conversion & Singing Voice Clone

Official PyTorch implementation for "Large Language Diffusion Models"

Container runtimes on macOS (and Linux) with minimal setup

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

💫 Toolkit to help you get started with Spec-Driven Development

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

Bringing BERT into modernity via both architecture changes and scaling

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

YaFSDP: Yet another Fully Sharded Data Parallel

AutoRAG: An Open-Source Framework for Retrieval-Augmented Generation (RAG) Evaluation & Optimization with AutoML-Style Automation

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

Updating this repo every week, You may want to STAR it :)

Supercharge Your LLM Application Evaluations 🚀

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

[2025-TMLR] A Survey on the Honesty of Large Language Models

Load and performance benchmark tool

Data and code for FreshLLMs (https://arxiv.org/abs/2310.03214)

A collection of large question answering datasets

Hackable and optimized Transformers building blocks, supporting a composable construction.

This is the repository of HaluEval, a large-scale hallucination evaluation benchmark for Large Language Models.

An implementation of Defeasible Logic in Python