🟣 Pytorch interview questions and answers to help you prepare for your next machine learning and data science interview in 2026.

100 个 PyTorch Tensor 练习题（带答案）

每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈

Kaggle notebook for ComfyUI

✔（已完结）超级全面的 深度学习 笔记【土堆 Pytorch】【李沐 动手学深度学习】【吴恩达 深度学习】【大飞 大模型Agent】

Open-source and strong foundation image recognition models.

这是一个clip-pytorch的模型，可以训练自己的数据集。

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Huggingface transformers的中文文档

Images to inference with no labeling (use foundation models to train supervised models).

Repo for Qwen Image Finetune

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

Fast inference from large lauguage models via speculative decoding

📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉

SGLang is a high-performance serving framework for large language models and multimodal models.

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

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

本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）

An open-source framework for training large multimodal models.

基于开源预训练模型来实现一个简单的CLIP模型

reasoning-from-scratch的中文翻译版本

Implement a reasoning LLM in PyTorch from scratch, step by step

『ゼロから作る Deep Learning ❹』(O'Reilly Japan, 2022)

『ゼロから作る Deep Learning ❺』(O'Reilly Japan, 2024)

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Jupyter notebooks for the Natural Language Processing with Transformers book

Natural Language Processing with Transformers 中译本，最权威Transformers教程

Langflow is a powerful tool for building and deploying AI-powered agents and workflows.