Tongxuan Liu's repositories
Megatron-LM
Ongoing research training transformer models at scale
tensorflow
An Open Source Machine Learning Framework for Everyone
FasterTransformer
Transformer related optimization, including BERT, GPT
flash-attention
Fast and memory-efficient exact attention
langchain
⚡ Building applications with LLMs through composability ⚡
LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
ScaleLLM
A high-performance inference system for large language models, designed for production environments.
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
AutoGPT
An experimental open-source attempt to make GPT-4 fully autonomous.
dlrover
DLRover: An Automatic Distributed Deep Learning System
libxsmm
Library targeting Intel Architecture for specialized dense and sparse matrix operations, and deep learning primitives.
llama2.c
Inference Llama 2 in one file of pure C
MetaGPT
🌟 The Multi-Agent Framework: Given one line Requirement, return PRD, Design, Tasks, Repo
metaseq
Repo for external large-scale work
mlc-llm
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
OpenAgents
OpenAgents: An Open Platform for Language Agents in the Wild
proposing-projects
This repo contains the LF AI & Data Project Proposal Process and Project Lifecycle. They explain the process to host new projects in LF AI & Data and provide a proposal template.
rules_boost
bazel build rules to use boost in bazel projects
serving
A flexible, high-performance serving system for machine learning models
triton
Development repository for the Triton language and compiler
Voyager
An Open-Ended Embodied Agent with Large Language Models