Stars
Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation
My learning notes for ML SYS.
Train your AI self, amplify you, bridge the world
Official repo for the paper "Scaling Synthetic Data Creation with 1,000,000,000 Personas"
3x Faster Inference; Unofficial implementation of EAGLE Speculative Decoding
Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
SGLang is a high-performance serving framework for large language models and multimodal models.
Build datasets using natural language
mllm-npu: training multimodal large language models on Ascend NPUs
Curated collection of papers in machine learning systems
🔥Highlighting the top ML papers every week.
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…
MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.
Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.
Cross-platform, customizable ML solutions for live and streaming media.
Petastorm library enables single machine or distributed training and evaluation of deep learning models from datasets in Apache Parquet format. It supports ML frameworks such as Tensorflow, Pytorch…
A complete computer science study plan to become a software engineer.
Apache OpenWhisk is an open source serverless cloud platform
Apache Nemo (Incubating) - Data Processing System for Flexible Employment With Different Deployment Characteristics