GPU 性能与 AI Infra 学习项目：CUDA/Triton 算子、NCU/NSYS、vLLM/SGLang/TRT-LLM/ms-swift、PyTorch/DeepSpeed/ms-swift 训练、并行架构
☆127Sep 8, 2026Updated last month
Alternatives and similar repositories for GPU-Perf-Playground
Users that are interested in GPU-Perf-Playground are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- MoLA Unified Human Motion Pretraining☆200Jul 13, 2026Updated 3 months ago
- RinCore - Fork of RikkaHub with modifications☆46Updated this week
- ☆84May 15, 2026Updated 5 months ago
- Android 端 AI 聊天 + 本地工具 Agent☆113Updated this week
- This system can help bridge the gap between Codex and Claude Code, making it simple to refine a plan until it is complete, or to conduct …☆484Aug 11, 2026Updated 2 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆106Sep 15, 2026Updated last month
- See through the fog of local development ports.☆490Aug 14, 2026Updated 2 months ago
- EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluati…☆439Updated this week
- CraftStation Agent Runtime Composition System☆680Updated this week
- A zero-dependency TypeScript memory kernel that gives any agent long-term memory. No training or backpropagation: each output reads a few…☆101Oct 4, 2026Updated 2 weeks ago
- 专为 DeepSeek Harness 打造的 AI 桌面工作台☆66Aug 20, 2026Updated last month
- A desktop app for autonomous AI digital employees — with an offline-first local knowledge base and an extensible plugin ecosystem.☆227Updated this week
- Native DeepSeek Harness (DSH) plugin integrating TypeSafe Jev or Decision api like luna as a System One decision layer for agent selectio…☆207Updated this week
- Reusable TypeScript workflow for Cocos Creator and WeChat Mini Games☆198Aug 23, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Self-hosted employee onboarding, policy learning, and assessment platform.☆198Oct 9, 2026Updated last week
- IdempotencyLab(幂等契约测试框架)：自动模拟并发、超时重试、MQ 重复消费等线上异常场景，验证支付 / 电商 / 库存系统的接口、MQ 消费与回调幂等实现是否真正可靠。☆100Aug 30, 2026Updated last month
- ☆115Sep 19, 2026Updated 3 weeks ago
- 面向 AI 上下文管理的 Agent Skill：为 Codex 上下文管理、Cursor 上下文切换和 Claude 上下文管理提供跨窗口续接，用 Git 保存可验证的功能说明与变更记录。AI coding context management and agent han…☆105Sep 7, 2026Updated last month
- Bounded project-memory skills for Codex CLI and Claude Code.☆496Sep 8, 2026Updated last month
- [Public alpha] Probability forecasting protocols, delayed-reward agent rollouts, and verifiable real-world task environments.☆159Sep 28, 2026Updated 2 weeks ago
- DeepSeek Harness 软件公司模式 preset：模拟真实软件公司分部门开发（需求冻结为 Sprint 合同、编码/验收独立、失败硬路由），用户作为公司总监在可视化大画布实时管理进度、子代理调用与 Token，用组织结构对抗长期上下文噪点导致的开发目标跑偏。☆122Aug 18, 2026Updated last month
- 这是一项关于基于肠口轴的进行多元分析结肠疾病，并可以给出有限药学建议的平台，但是需要注明的是，本平台给出的结果绝对不可以当作真实疾病诊断，仅可做风险监测，避免不必要的过度诊疗。如在本平台检测有高风险且有明显临床不适时，请尽快就医，以免贻误病情。☆127Aug 21, 2026Updated last month
- project nexus pmp☆101Sep 2, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ROS Noetic 两轮差速自主移动机器人：ESP32 底盘(PID/编码器/IMU) + J1900 车载(LiDAR/相机) + PC(SLAM/导航/人体跟随)，三机分布式全链路开源实现☆106Updated this week
- Open-source multi-model desktop group chat and Chrome extension☆212Sep 24, 2026Updated 3 weeks ago
- ☆107Sep 24, 2026Updated 3 weeks ago
- Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-…☆1,006Updated this week
- An end-to-end growth tool that understands the product, fetch the data it needs, researches the market, executes campaigns, and reviews r…☆1,992Sep 28, 2026Updated 2 weeks ago
- 从 0 训练大模型，单卡训练一个 200M 参数模型的全流程（train a 200M‑parameter model from scratch）☆62Sep 23, 2026Updated 3 weeks ago
- Auditable LLM multi-agent town simulation with AgentScope, Mesa, replay, policy experiments, and Streamlit☆101Sep 29, 2026Updated 2 weeks ago
- [Public preview] An advanced AI Benchmark for math, produced by mathmo at St John's College, Cambridge.☆101Sep 24, 2026Updated 3 weeks ago
- Live M1 candles rendered inside M5 bars for ATAS Classic.☆100Aug 13, 2026Updated 2 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- ☆820Updated this week
- AI-native, local-first video editor by Ribbi — runs entirely in the browser. Rust/WASM engine, WebGPU compositing, WebCodecs export; huma…☆455Updated this week
- ☆230Updated this week
- Pentest anything you want☆116Sep 21, 2026Updated 3 weeks ago
- An open-source virtual AI Infra team that discovers, benchmarks, and safely upgrades local LLM inference—with independent quality gates, …☆97Sep 8, 2026Updated last month
- Z.ai's coding agent harness. Powerful, intelligent, extensible.☆122Oct 10, 2026Updated last week
- Agent Skill 步进治理体系：由程序保证 Agent 不跳步骤（step-gate Rust 门控 + 交付门 + 链治理）☆479Sep 5, 2026Updated last month