doldre

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

pytorch-lightning

Pretrain, finetune and deploy AI models on multiple GPUs, TPUs with zero code changes.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

LLaVA

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

llama2.c

Inference Llama 2 in one file of pure C

immersive-translate

沉浸式双语网页翻译扩展 , 支持输入框翻译， 鼠标悬停翻译， PDF, Epub, 字幕文件, TXT 文件翻译 - Immersive Dual Web Page Translation Extension

flash-attention

Fast and memory-efficient exact attention

mamba

Mamba SSM architecture

Awesome-Multimodal-Large-Language-Models

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

Megatron-LM

Ongoing research training transformer models at scale

LAVIS

LAVIS - A One-stop Library for Language-Vision Intelligence

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

GPU-Puzzles

Solve puzzles. Learn CUDA.

QuantsPlaybook

量化研究-券商金工研报复现

DeepRL

Deep Reinforcement Learning Lab, a platform designed to make DRL technology and fun for everyone

llm-awq

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

FinRL-Trading

For trading. Please star.

randomfun

Notebooks and various random fun

rq-vae-transformer

The official implementation of Autoregressive Image Generation using Residual Quantization (CVPR '22)

LongNet

Implementation of plug in and play Attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

M5-methods

Data, Benchmarks, and methods submitted to the M5 forecasting competition

RL-book

bigcode-dataset

hive-third-functions

Some useful custom hive udf functions, especial array, json, math, string functions.

aqt

Reinforcement-Learning-for-Market-Making

Using tabular and deep reinforcement learning methods to infer optimal market making strategies

VidToMe

Official Pytorch Implementation for "VidToMe: Video Token Merging for Zero-Shot Video Editing" (CVPR 2024)

ffrecord

FireFlyer Record file format, writer and reader for DL training samples.

DisCo-CLIP

Official PyTorch implementation of the paper "DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training".