A from-scratch Prefill/Decode disaggregation inference engine for LLMs
☆163May 10, 2026Updated 3 months ago
Alternatives and similar repositories for nanoPD
Users that are interested in nanoPD are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A multifunctional Java auditing assistant with a LLM module☆23Apr 9, 2026Updated 4 months ago
- Apple Server APIs for Go☆36Dec 25, 2025Updated 8 months ago
- The Ultimate "Token Saver"☆62May 7, 2026Updated 3 months ago
- OfCourse I Code the Quintessence☆33Mar 31, 2026Updated 5 months ago
- Claude Code 源码逆向恢复项目 | Source Map 逆向 · 架构分析 · 可运行版本 | 1900+ 文件 · 51万行代码 · 12章节课程☆57Updated this week
- 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.
- ☆28Apr 10, 2026Updated 4 months ago
- ☆32Apr 11, 2026Updated 4 months ago
- ☆42Jul 28, 2026Updated last month
- 将抖音视频转化为结构化的深度学习笔记，并沉淀为可被mcp调用的sql知识库。☆45Aug 15, 2026Updated 2 weeks ago
- Project: Autoresearch Foundry☆16Apr 24, 2026Updated 4 months ago
- 🎱 AI Agent Governance Framework — Constrain how AI Agents behave in your project. pip install pattern8☆49Mar 24, 2026Updated 5 months ago
- 🤖 AI-powered video note-taking application that transforms audio and video content into structured text notes.☆34Apr 1, 2026Updated 5 months ago
- Introduction for the Black Horse AI video generator: HappyHorse 1.0. Updates at:☆127Apr 10, 2026Updated 4 months ago
- Awesome CoT for Autonomous Driving☆102Feb 25, 2026Updated 6 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.
- Native desktop GUI for Claude Code and Codex CLI.☆115Aug 10, 2026Updated 3 weeks ago
- An Open-Source Scaling Framework for Domain Specific Architectures☆61Updated this week
- claude-code-java 是一个可嵌入任何 Java 应用的 AI Agent 引擎。claude-code-java is an embeddable AI Agent engine for Java applications.☆47May 10, 2026Updated 3 months ago
- C3Box: A CLIP-based Class-Incremental Learning Toolbox☆95Apr 21, 2026Updated 4 months ago
- A lightweight, event-driven multi-agent framework for embodied AI systems.☆138Aug 16, 2026Updated 2 weeks ago
- Implementation of the IJCV 2026 paper "SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition".☆49Apr 25, 2026Updated 4 months ago
- Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optu…☆222Updated this week
- ☆188Jun 15, 2026Updated 2 months ago
- ☆15Apr 10, 2026Updated 4 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ReactMotion: Generating Reactive Listener Motions from Speaker Utterance☆99Mar 30, 2026Updated 5 months ago
- [ICLR 2026] PAGE-4D: Disentangled Pose and Geometry Estimation for VGGT-4D Perception☆230Aug 4, 2026Updated 3 weeks ago
- [CVPR 2026] Official PyTorch implementation of WaDi: Weight Direction-aware Distillation for One-step Image Synthesis☆192May 26, 2026Updated 3 months ago
- ☆109Updated this week
- Python-based quant trading research project for short-term reversal option setups, universe selection, staged-entry backtesting, and live…☆257Updated this week
- An AI dataset index covering major research areas☆31Apr 25, 2026Updated 4 months ago
- A Claude Code skill that burns tokens on demand. Stress test, inflate metrics, or just set money on fire.☆177May 3, 2026Updated 3 months ago
- Agent skill for AWP RootNet protocol (testnet) — query, stake, govern, and monitor on-chain☆237May 2, 2026Updated 4 months ago
- 这是一个本地化软件供应链安全扫描工具，支持依赖风险分析、SBOM 生成、安全闸门与 OSV 漏洞查询。☆394May 31, 2026Updated 3 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- [ICLR 2026] Multi-Head Low-Rank Attention☆33Apr 16, 2026Updated 4 months ago
- Sync AI context across every terminal window. 3 seconds to know what to work on next.☆349May 7, 2026Updated 3 months ago
- Clouds Coder is a local-first coding agent platform centered on separating the CLI execution plane from the Web user plane, with Web UI, …☆294Updated this week
- ☆232Jul 29, 2026Updated last month
- Official inference code for SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing.☆207Jun 30, 2026Updated 2 months ago
- See when AI is making things up.Make AI more honest — and show its receipts.☆36Apr 30, 2026Updated 4 months ago
- 以协议核心的 AI 项目工作流系统，支持 skills 驱动、change 队列与 Codex/Claude Code 协作。☆95Apr 1, 2026Updated 5 months ago