An open-source, high-performance SQL vector database built on ClickHouse.

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

Building a quick conversation-based search demo with Lepton AI.

Unofficial implementation of InstantID for ComfyUI

High-speed Large Language Model Serving on PCs with Consumer-grade GPUs

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

Crawl a site to generate knowledge files to create your own custom GPT from a URL

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

This repository contains a collection of resources and papers on Diffusion Models for RL, accompanying the paper "Diffusion Models for Reinforcement Learning: A Survey"

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

Serving multiple LoRA finetuned LLM as one

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

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

Inference code for Llama models

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

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

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

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

Unified Reinforcement Learning Framework

🦜🔗 Build context-aware reasoning applications

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

《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。

Semantic Image Synthesis with SPADE

A text generation benchmarking platform

AirConcurrentMap is a fast, memory efficient Java ConcurrentNavigableMap implementation

HttpRunner 是一个开源的 API/UI 测试工具，简单易用，功能强大，具有丰富的插件化机制和高度的可扩展能力。

Write scalable load tests in plain Python 🚗💨

Implementing Recurrent Neural Network from Scratch

ACM_Website_2014_Develop