国科大硕士/博士学位论文LeTeX模板, 以《中国科学院大学研究生学位论文撰写规范指导意见》(校发学位字[2022]40号, 附件1) 作为撰写要求

LaTeX Thesis Template for the University of Chinese Academy of Sciences

黑马程序员最新Java项目实战《苍穹外卖》，最适合新手的SpringBoot+SSM企业级项目实战 相比于瑞吉外卖苍穹外卖的业务更加真实完整，用户端改为微信小程序，登录改为了微信登录，加入了统计报表，来单提醒，客户催单，订单管理等功能，业务实现了闭环。技术选型更加丰富和实用。可以认为是增强版瑞吉外卖

推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/

Easy-to-Use RAG Framework; CCF AIOps International Challenge 2024 Top3 Solution; CCF AIOps 国际挑战赛 2024 季军方案

本项目为书籍《大模型RAG实战》的代码以及资料汇总。

向量检索与 RAG 实践：技术、实现与应用

大模型/LLM推理和部署理论与实践

EfficientFormerV2 [ICCV 2023] & EfficientFormer [NeurIPs 2022]

Quantized Attention that achieves speedups of 2.1-3.1x and 2.7-5.1x compared to FlashAttention2 and xformers, respectively, without lossing end-to-end metrics across various models.

Training-free Post-training Efficient Sub-quadratic Complexity Attention. Implemented with OpenAI Triton.

Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers

Development repository for the Triton language and compiler

Simplify your onnx model

Inference optimization of the ViT model using TensorRT, NVIDIA's high-performance deep learning inference platform. TensorRT is designed to maximize the efficiency of deep learning models during in…

TensorRT 2022 亚军方案，tensorrt加速mobilevit模型

Flash Attention in ~100 lines of CUDA (forward pass only)

how to optimize some algorithm in cuda.

A unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deploym…

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

This is the official code for paper: Token Summarisation for Efficient Vision Transformers via Graph-based Token Propagation