TinyChatEngine: On-Device LLM Inference Library

高性能并行编程与优化 - 课件

A curated list of awesome C++ (or C) frameworks, libraries, resources, and shiny things. Inspired by awesome-... stuff.

【A common used C++ DAG framework】 一个通用的、无三方依赖的、跨平台的、收录于awesome-cpp的、基于流图的并行计算框架。欢迎star & fork & 交流

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

[NeurIPS'24 Spotlight] EVE: Encoder-Free Vision-Language Models

VisionLLM Series

LLM training in simple, raw C/CUDA

📚200+ Tensor/CUDA Cores Kernels, ⚡️flash-attn-mma, ⚡️hgemm with WMMA, MMA and CuTe (98%~100% TFLOPS of cuBLAS/FA2 🎉🎉).

Universal LLM Deployment Engine with ML Compilation

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

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）

LLM Tokenizer with BPE algorithm