tiantang5156

lectures

Material for cuda-mode lectures

torchsparse

[MICRO'23, MLSys'22] TorchSparse: Efficient Training and Inference Framework for Sparse Convolution on GPUs.

pytorchvideo

A deep learning library for video understanding research.

yolo_slowfast

Yolov5+SlowFast: Realtime Action Detection Based on PytorchVideo

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

Custom-ava-dataset_Custom-Spatio-Temporally-Action-Video-Dataset

Custom ava dataset, Multi-Person Video Dataset Annotation Method of Spatio-Temporally Actions

SlowFast

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

llm.c

LLM training in simple, raw C/CUDA

tinyflow

Tutorial code on how to build your own Deep Learning System in 2k Lines

cuda_learning

learning how CUDA works

Awesome-LLM-Inference

📖A curated list of Awesome LLM Inference Paper with codes, TensorRT-LLM, vLLM, streaming-llm, AWQ, SmoothQuant, WINT8/4, Continuous Batching, FlashAttention, PagedAttention etc.

llama.cpp

LLM inference in C/C++

CVPR2024-Papers-with-Code

CVPR 2024 论文和开源项目合集

annotated_deep_learning_paper_implementations

🧑‍🏫 60 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

Programmers-Overseas-Job-Interview-Handbook

🏂🏻 程序员海外工作/英文面试手册

EmbedRoadAndCSInEU

嵌入式软件之路与欧陆CS留学工作

tinyflow

A simple deep learning framework that supports automatic differentiation and GPU acceleration.

axolotl

Go ahead and axolotl questions

triton

Development repository for the Triton language and compiler

pytorch-lightning

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

lora_from_scratch

Implements Low-Rank Adaptation(LoRA) Finetuning from scratch

self-llm

《开源大模型食用指南》基于Linux环境快速部署开源大模型，更适合**宝宝的部署教程

Tianji

天机是一款专注人情世故的大语言模型系统。您可以利用它进行涉及传统人情世故的任务，如何说好话、如何会来事儿等，以提升您的“情商”和"核心竞争能力"

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

ChatGLM-6B

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

ChatGLM-Finetuning

基于ChatGLM-6B、ChatGLM2-6B、ChatGLM3-6B模型，进行下游具体任务微调，涉及Freeze、Lora、P-tuning、全参微调等

CUDA-Learn-Notes

🎉CUDA/C++ 笔记 / 大模型手撕CUDA / 技术博客，更新随缘: flash_attn、sgemm、sgemv、warp reduce、block reduce、dot product、elementwise、softmax、layernorm、rmsnorm、hist etc.

tcu_scope

Atom

[MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving

web-llm

High-performance In-browser LLM Inference Engine