iofu728

open-interpreter

A natural language interface for computers

autogen

A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap

ChatGLM3

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

promptflow

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

TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

make-real

Draw a ui and make it real

alignment-handbook

Robust recipes to align language models with human and AI preferences

OpenAgents

OpenAgents: An Open Platform for Language Agents in the Wild

consistencydecoder

Consistency Distilled Diff VAE

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

prompt2model

prompt2model - Generate Deployable Models from Natural Language Instructions

AgentBench

A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

FlexFlow

FlexFlow Serve: Low-Latency, High-Performance LLM Serving

elog

Markdown 批量导出工具、开放式跨平台博客解决方案，随意组合写作平台(语雀/Notion/FlowUs/飞书)和博客平台(Hexo/Vitepress/Halo/Confluence/WordPress等)

open-instruct

Llama-2-Onnx

LookaheadDecoding

SparsePrimingRepresentations

Public repo to document some SPR stuff

MS-AMP

Microsoft Automatic Mixed Precision Library

LLM-Shearing

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

gpt_paper_assistant

GPT4 based personalized ArXiv paper assistant bot

llamafia.github

qmoe

Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".

flash-fft-conv

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

langsuite

Official Repo of LangSuitE

FeAT

[NeurIPS 2023] Understanding and Improving Feature Learning for Out-of-Distribution Generalization