Several optimization methods of half-precision general matrix vector multiplication (HGEMV) using CUDA core.

Running large language models on a single GPU for throughput-oriented scenarios.

Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruction.

[VLDB'22] Anomaly Detection using Transformers, self-conditioning and adversarial training.

带你从零实现一个高性能的深度学习推理库，Implement a high-performance deep learning inference library step by step

A Deep Reinforcement Learning enhanced Kubernetes Scheduler for Microservice-based System

High-performance Stream Processing Framework. An alternative to Apache Flink.

纯c++的全平台llm加速库，支持python调用，chatglm-6B级模型单卡可达10000+token / s，支持glm, llama, moss基座，手机端流畅运行

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Learning Vim and Vimscript doesn't have to be hard. This is the guide that you're looking for 📖

Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

You like pytorch? You like micrograd? You love tinygrad! ❤️

A professionally curated list of awesome resources (paper, code, data, etc.) on Self-Supervised Learning for Time Series (SSL4TS).

A fast multi-producer, multi-consumer lock-free concurrent queue for C++11

how to optimize some algorithm in cuda.

a lightweight LLM model inference framework

A retargetable MLIR-based machine learning compiler and runtime toolkit.

🎉 Repo for LaWGPT, Chinese-Llama tuned with Chinese Legal knowledge. 基于中文法律知识的大语言模型

[NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 2…

A lightweight parameter server interface

Learning material for CMU10-714: Deep Learning System

Smart Pointers implementation (std::unique_ptr, std::shared_ptr)