🦜🔗 Build context-aware reasoning applications

《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。

Inference code for Llama models

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Write scalable load tests in plain Python 🚗💨

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

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

Running large language models on a single GPU for throughput-oriented scenarios.

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

GLM-130B: An Open Bilingual Pre-Trained Model (ICLR 2023)

Semantic Image Synthesis with SPADE

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

Unofficial implementation of InstantID for ComfyUI

Serving multiple LoRA finetuned LLM as one

A text generation benchmarking platform

Unified Reinforcement Learning Framework

Implementing Recurrent Neural Network from Scratch