dyedd
Follow
Lists (2)
Stars
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga…
LLM notes, including model inference, transformer model structure, and llm framework code analysis notes.
A curated list of resources for using LLMs to develop more competitive grant applications.
🔥中文 prompt 精选🔥，ChatGPT 使用指南，提升 ChatGPT 可玩性和可用性！🚀
🚀 原生使用 Deepspeed 训练 Diffusers | Native Training of Diffusers with Deepspeed
Various AI scripts. Mostly Stable Diffusion stuff.
A general fine-tuning kit geared toward diffusion models.
A survey and paper list of current Diffusion Model for Time Series and SpatioTemporal Data with awesome resources (paper, application, review, survey, etc.).
📖A curated list of Awesome Diffusion Inference Papers with codes, such as Sampling, Caching, Multi-GPUs, etc. 🎉🎉
Machine Learning Engineering Open Book
PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/Docker
SwissArmyTransformer is a flexible and powerful library to develop your own Transformer variants.
📚150+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
校招、秋招、春招、实习好项目！带你从零实现一个高性能的深度学习推理库，支持大模型 llama2 、Unet、Yolov5、Resnet等模型的推理。Implement a high-performance deep learning inference library step by step
🚀 Cross attention map tools for huggingface/diffusers
VideoSys: An easy and efficient system for video generation
Finetune Llama 3.3, Mistral, Phi, Qwen 2.5 & Gemma LLMs 2-5x faster with 70% less memory
End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (V…
Gensis is a lightweight deep learning framework written from scratch in Python, with Triton as its backend for high-performance computing.
Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research
Pytorch reimplementation of the Vision Transformer (An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale)