Lists (3)
Stars
[ICML 2026] EvoGM: Learning to Merge LLMs via Evolutionary Generative Optimization
Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows
Autoresearch for GPU kernels. Give it any PyTorch model, go to sleep, wake up to optimized Triton kernels.
EvoNAS is a framework for neural architecture search , implemented with PyTorch. It supports supernet training, evolutionary multi-objective optimization, and seamless integration with modern compu…
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
🚀 通用 AI IDE 账号管理工具：支持 Antigravity / Codex / GitHub Copilot / Windsurf / Kiro / Cursor / Gemini-cli / CodeBuddy，多账号切换、配额监控、自动唤醒与多开实例管理。 🚀 Universal AI IDE account manager for Antigravity / Codex / …
Official Problem Sets / Reference Kernels for the GPU MODE Leaderboard!
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
iStratDE is a GPU-accelerated Differential Evolution framework that enhances performance through individual-level strategy diversity. By assigning unique, fixed strategies to each individual at ini…
LibMOON is a standard and flexible framework to study gradient-based multiobjective optimization.
FastAPI framework, high performance, easy to learn, fast to code, ready for production
Evolutionary Generative Optimization(EvoGO) is a fully data-driven framework for black-box optimization.
"Paper2Slides: From Paper to Presentation in One Click"
A framework for efficient model inference with omni-modality models
A comprehensive list of gradient-based multi-objective optimization algorithms in deep learning.
A high-throughput and memory-efficient inference and serving engine for LLMs
Hydro - Next generation high performance online-judge platform - 新一代高效强大的信息学在线测评系统 (a.k.a. vj5)
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
Open source online judge based on Vue, Django and Docker. | 青岛大学开源 Online Judge | QQ群 496710125 | admin@qduoj.com
Popular Simple Open Source Online Judge based on PHP/C++/MySQL/Linux for ACM/ICPC and NOIP training, with easy installation. 简单实用的开源OJ系统
A spiking feature pyramid network with adaptive neurons for event-based vision tasks in autonomous driving, evaluated on GAD and N-CARS datasets.
Efficient method for accelerating spiking neuron computation on GPU, enabling faster SNN training. Includes demos and a self-buildable CUDA kernel tutorial.