Clone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT：gpt-image-2 仿版式、你换内容，另含 10 套精选风格。Claude Code / OpenCla…

LaTeX template for my personal resume

This repository is established to store personal notes and annotated papers during daily research.

NVIDIA Resiliency Extension is a python package for framework developers and users to implement fault-tolerant features. It improves the effective training time by minimizing the downtime due to fa…

Open-source framework for detecting Silent Data Corruption (SDC) in production GPU/accelerator clusters

An agentic skills framework & software development methodology that works.

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

The official implementation of ICLR26 poster, Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs.

[ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Anatomy of High-Performance GEMM with Online Fault Tolerance on GPUs

OpenShell is the safe, private runtime for autonomous AI agents.

Architecture-level Fault Injection Tool for GPU Application Resilience Evaluation

A runtime fault injection tool for PyTorch 🔥

Development repository for the Triton language and compiler

VSCode theme based off the easemate IDE and Jetbrains islands theme

A verification tool for ensuring parallelization equivalence in distributed model training.

An Observability Framework for AI Training

Build, deploy, and orchestrate AI agents. Sim is the central intelligence layer for your AI workforce.

My learning notes for ML SYS.

ncnn is a high-performance neural network inference framework optimized for the mobile platform

Fast and memory-efficient exact attention

重返未来：1999 小助手 | Assistant For Reverse: 1999

A privacy-first, self-hosted, fully open source personal knowledge management software, written in typescript and golang.

eBPF-based Networking, Security, and Observability

A feedback-driven fault injection tool for reproducing distributed systems failures

Automated Testing and Adaptive Detection of **Slow Faults** in Distributed Systems