weigao266

llama.cpp

LLM inference in C/C++

zed

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

google-research

Google Research

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

pytorch_geometric

Graph Neural Network Library for PyTorch

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

ChatPaper

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

flash-attention

Fast and memory-efficient exact attention

NeMo

A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Awesome-Multimodal-Large-Language-Models

:sparkles::sparkles:Latest Advances on Multimodal Large Language Models

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

torchmetrics

Torchmetrics - Machine learning metrics for distributed, scalable PyTorch applications.

GenerativeAIExamples

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

Megatron-DeepSpeed

Ongoing research training transformer language models at scale, including: BERT & GPT-2

bigscience

Central place for the engineering/scaling WG: documentation, SLURM scripts and logs, compute environment and data.

DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models

megablocks-public

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training

flash-linear-attention

Efficient implementations of state-of-the-art linear attention models in Pytorch and Triton

megablocks

Awesome-Mixture-of-Experts-Papers

A curated reading list of research in Mixture-of-Experts(MoE).

MS-AMP

Microsoft Automatic Mixed Precision Library

NeMo-Megatron-Launcher

NeMo Megatron launcher and tools

MathPile

Generative AI for Math: MathPile

zero-bubble-pipeline-parallelism

Zero Bubble Pipeline Parallelism

lightning-attention

Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models