Lists (26)
BEV
5 repositories
CMake
3 repositories
GAN
1 repository
Hackintosh
3 repositories
interesting network
2 repositories
KDE
1 repository
llm
8 repositories
ncnn
12 repositories
nvidia
11 repositories
ROS
4 repositories
tensorrt
2 repositories
vulkan
1 repository
三维重建
1 repository
人类语言
1 repository
匹配
1 repository
地空匹配
3 repositories
导航
19 repositories
找工作
3 repositories
有意思
29 repositories
有用的工具
20 repositories
汇总
2 repositories
画图
1 repository
目标检测
1 repository
路网
5 repositories
量化
6 repositories
面试
2 repositories
Starred repositories
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA/Tensor Cores Kernels, HGEMM, FA-2 MMA etc.🔥
bityj / bestcnvpn
Forked from bbbestb/bestcnvpn【国内梯子排行】最好用的VPN梯子推荐与科学上网测评 -梯子、科学上网、翻墙、机场、v2ray、trojan、shadowsock
1
Updated Dec 15, 2023
how to optimize some algorithm in cuda.
Make RepVGG Greater Again: A Quantization-aware Approach
A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (p…
Docker image for Remote Desktop server with audio support
中文的C++ Template的教学指南。与知名书籍C++ Templates不同，该系列教程将C++ Templates作为一门图灵完备的语言来讲授，以求帮助读者对Meta-Programming融会贯通。(正在施工中)
本项目是一个通过文字生成图片的项目，基于开源模型Stable Diffusion V1.5生成可以在手机的CPU和NPU上运行的模型，包括其配套的模型运行框架。
👩🏿💻👨🏾💻👩🏼💻👨🏽💻👩🏻💻中国独立开发者项目列表 -- 分享大家都在做什么
Open-Sora: Democratizing Efficient Video Production for All
Universal cross-platform tokenizers binding to HF and sentencepiece
Analyze the inference of Large Language Models (LLMs). Analyze aspects like computation, storage, transmission, and hardware roofline model in a user-friendly interface.
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
The stable diffusion webui training aid extension helps you quickly and visually train models such as Lora.
让微信网页版可用 / Allow the use of WeChat via webpage access
llm deploy project based mnn. This project has merged into MNN.
崩坏：星穹铁道脚本 | Honkai: Star Rail auto bot (简体中文/繁體中文/English/Español)
TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and support state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorR…
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）
fastllm是后端无依赖的高性能大模型推理库。同时支持张量并行推理稠密模型和混合模式推理MOE模型，任意10G以上显卡即可推理满血DeepSeek。双路9004/9005服务器+单显卡部署DeepSeek满血满精度原版模型，单并发20tps；INT4量化模型单并发30tps，多并发可达60+。
整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。