Stars
A composable library of skills and rules for AI coding agents. Covers repo memory, long-horizon execution, multi-agent coordination, TDD, security review, and delivery automation.
End-to-end benchmark for AI-generated GPU kernels, drawn from real production traces — turn a PyTorch reference into a DSL kernel (Triton, Gluon, FlyDSL, CuteDSL) and grade it on compilation, numer…
An end-to-end agent project for GPU kernel implementation, analysis, profiling, and iterative optimization. It helps an agent turn PyTorch logic or an existing kernel into a high-performance GPU ke…
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
[EuroSys'26] FlashPS: Efficient Generative Image Editing with Mask-aware Caching and Scheduling
[ATC'25] Katz is a high-performance serving system designed specifically for diffusion model workflows with multiple adapters.
Here are my personal paper reading notes (including machine learning systems, AI infrastructure, and other interesting stuffs).
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…
A library to inspect and extract intermediate layers of PyTorch models.
An improved PPO algorithm using RND (Random Network Distillation). Tested in Google Research Football.
Modularized Implementation of Deep RL Algorithms in PyTorch
A large-scale 7B pretraining language model developed by BaiChuan-Inc.
Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.
Research Trends in LLM-guided Multimodal Learning.
Open source implementation of the PAAC algorithm presented in Efficient Parallel Methods for Deep Reinforcement Learning
A curated list of reinforcement learning with human feedback resources (continually updated)
Train transformer language models with reinforcement learning.
A high-performance distributed training framework for Reinforcement Learning
Anonymous Github is a proxy server to support anonymous browsing of Github repositories for open-science code and data.
A collection of mini-programs demonstrating Kubernetes client-go usage.
Kubectl plugin to ease sniffing on kubernetes pods using tcpdump and wireshark
《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）
A small demo/experiment that shows how Linux process IDs (PIDs) can be mapped to Kubernetes pod metadata.