[ICLR 2026] Official pytorch implementation of The Unseen Frontier: Pushing the Limits of LLM Sparsity with Surrogate-Free ADMM

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

[ICLR 2024] Dynamic Sparse Training with Structured Sparsity

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

Code for Winning the Lottery Ahead of Time: Efficient Early Network Pruning (ICML 2022)

Introduction to Parallel Programming class code

Material for gpu-mode lectures

🧠「大模型」2小时完全从0训练64M的小参数LLM！Train a 64M-parameter LLM from scratch in just 2h!

List of AI Residency Programs

This repository is a curated collection of resources, tutorials, and practical examples designed to guide you through the journey of mastering CUDA programming. Whether you're just starting or look…

InferX: Inference as a Service Platform

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

The fastai deep learning library

Clinical NLP Shared Task @ NAACL'24

DSPy: The framework for programming—not prompting—language models

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients. Published in Nature.

You like pytorch? You like micrograd? You love tinygrad! ❤️

[NeurIPS'22] EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records

Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.

Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

[ACL 2025 Industry Track, Oral] Sentiment Reasoning for Healthcare

An associative memory system that stores and retrieves experiences using the 5W1H framework (Who, What, When, Where, Why, How) and content-addressable memory.

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using Agentic Retrieval 🔄.

🚀 The fast, Pythonic way to build MCP servers and clients.

A framework for prompt tuning using Intent-based Prompt Calibration

Build Real-Time Knowledge Graphs for AI Agents

Code for Retrieval augmented text-to-SQL generation for epidemiological question answering using electronic health records