awesome-distributed-ml

A curated list of awesome projects and papers for distributed training or inference

awesome-self-supervised-learning-timeseries

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

bovim

cbcompiler

A compiler made by CB

cbrpc

c++ async rpc framework. 14w+qps.

cmu10-714

Learning material for CMU10-714: Deep Learning System

concurrentqueue

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

cost-model-papers

cuda-neural-network

Convolutional Neural Network with CUDA (MNIST 99.23%)

cuda_hgemm

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

cuda_hgemv

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

distributed-futures

Implementation of the future shared memory synchronization model for distributed memory

drs

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

effective_transformer

Running BERT without Padding

fancy_cuda

fastllm

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

flexgen

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

fuckcpp

gnnhwc

A CUDA kernel for NHWC GroupNorm for PyTorch

hardware-effects-gpu

Demonstration of various hardware effects on CUDA GPUs.

how-to-optim-algorithm-in-cuda

how to optimize some algorithm in cuda.

inference_server

inferllm

a lightweight LLM model inference framework

iree

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

javafxcanvas

A Canvas made by JavaFx

javaweb

kernl

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.

ksanallm

kuiperinfer

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

lawgpt

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