Stars
Supercharge Your LLM with the Fastest KV Cache Layer
A high-throughput and memory-efficient inference and serving engine for LLMs
SGLang is a high-performance serving framework for large language models and multimodal models.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
MNN is a blazing fast, lightweight deep learning framework, battle-tested by business-critical use cases in Alibaba. Full multimodal LLM Android App:[MNN-LLM-Android](./apps/Android/MnnLlmChat/READ…
Universal LLM Deployment Engine with ML Compilation
Tile-Based Runtime for Ultra-Low-Latency LLM Inference
High-performance inference framework for large language models, focusing on efficiency, flexibility, and availability.
AISystem 主要是指AI系统,包括AI芯片、AI编译器、AI推理和训练框架等AI全栈底层技术
AIInfra(AI 基础设施)指AI系统从底层芯片等硬件,到上层软件栈支持AI大模型训练和推理。
High-speed Large Language Model Serving for Local Deployment
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
MiniCPM4 & MiniCPM4.1: Ultra-Efficient LLMs on End Devices, achieving 3+ generation speedup on reasoning tasks
A case study of quantitative modeling for beginners.
LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.
《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调(全参数/Lora)、部署国内外开源大模型(LLM)/多模态大模型(MLLM)教程
LLMs-from-scratch项目中文翻译
🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT!🌏 Train a 26M-parameter GPT from scratch in just 2h!
A Library for Advanced Deep Time Series Models for General Time Series Analysis.
Time series Timeseries Deep Learning Machine Learning Python Pytorch fastai | State-of-the-art Deep Learning library for Time Series and Sequences in Pytorch / fastai
This repository is transfered from the personal account of Dr. Zhognwei Deng (Michael Teng)
An Autonomous LLM Agent for Complex Task Solving
研究生数学建模,本科生数学建模、数学建模竞赛优秀论文,数学建模算法,LaTeX论文模板,算法思维导图,参考书籍,Matlab软件教程,PPT
✔️李沐 【动手学深度学习】课程学习笔记:使用pycharm编程,基于pytorch框架实现。
Java 学习&面试指南(Go、Python 后端面试通用,计算机基础面试总结)。准备后端技术面试,首选 JavaGuide!