Learn DeepInfer through a small, runnable inference engine. Follow the code on CPU, then run real Qwen3.5 models on Ascend 910C.
☆28Oct 25, 2026Updated this week
Alternatives and similar repositories for mini-deepinfer
Users that are interested in mini-deepinfer are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- The open registry and delivery platform for agent skills.☆267Sep 17, 2026Updated last month
- ☆206Updated this week
- A tool for detecting screenshot, screen recording, and screen sharing activities on Android from an application-layer perspective. Comple…☆98Oct 4, 2026Updated 3 weeks ago
- EdgeRock: Strong Reasoning at Constant Memory. Multimodal models with O(N) generation and O(1) persistent history. Inference and evaluati…☆709Updated this week
- 一条命令，把口播毛片变成可二次精修的剪辑工程。☆966Updated 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.
- CraftStation Agent Runtime Composition System☆880Updated this week
- LLM-first, 3D-native robotics and simulation workspace.☆879Updated this week
- Run Linux-style commands on Windows via deterministic bash→PowerShell translation. No VM, no WSL. MCP server + CLI built for AI agents (C…☆903Updated this week
- 软件实习项目作业☆989Sep 2, 2026Updated last month
- ☆833Updated this 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）☆678Sep 5, 2026Updated last month
- OntiCards 是面向企业的 AI 数据中枢（AI Data Hub），围绕业务数据库提供一站式能力：数据源连接、元数据理解、自然语言查询、跨源融合、数据质检、查询审计与数据资产管理等☆611Updated this week
- Android 端 AI 聊天 + 本地工具 Agent☆186Oct 19, 2026Updated last week
- Free strategy scorecard for trading backtests. Detect overfitting, weak edge, drawdown risk, and random-timing luck from returns, equity …☆931Updated this week
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- A fast coding agent, rpc plugin, sub-agents, sloppy edits, and mcp☆744Updated this week
- Governance standard and reference toolset for LLM-maintained knowledge corpora☆641Sep 12, 2026Updated last month
- Flatkey media generation CLI for images, videos, audio, text, credits, and model discovery.☆875Updated this week
- FactCircuit: an auditable claim-and-evidence verification loop with immutable provenance, staged checks, bounded retrieval, and reproduci…☆918Oct 9, 2026Updated 3 weeks ago
- 希儿最初的家~☆734Updated this week
- Local-first AI agent workspace for multi-agent collaboration, agent orchestration, scoped permissions, evidence-aware runs, and human-in-…☆1,183Updated this week
- 基于 Jingyun Studio + DeepSeek Harness (DSH) 打造的一站式 AI 商业化桌面客户端，一个将 AI 智能体 / 技能 / 工作流转化为可交易商品的完整商业化平台客户端。 井云为 DSH 注入了完整的商业闭环：登录注册 → 会员体系 →…☆924Sep 30, 2026Updated 3 weeks ago
- Qyclaw 可以理解为一个“平台化的智能体操作系统”： - 上层是多用户、多会话、多技能、多连接器的平台能力 - 中间是队列、调度、记忆、权限、审计等运行时编排能力 - 下层是容器化工具执行沙箱☆191Apr 10, 2026Updated 6 months ago
- Hojo-ASR is a high-performance speech recognition model powered by the LLM decoder.☆473May 26, 2026Updated 5 months ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆121Oct 13, 2026Updated 2 weeks ago
- DeepAgent Code: AI coding agent with persistent memory and control plane☆432Updated this week
- Token-scale scientific discovery engine — autonomous hypothesis generation, experiment execution, and knowledge graph synthesis☆377Updated this week
- When AI replaces everything, how long can you survive?☆94Sep 30, 2026Updated 3 weeks ago
- Open-source 3D AI companion and transparent desktop pet. Also: 开源 3D AI 伴侣, 本地 3D 陪玩, 虚拟陪玩, 透明桌宠. Desktop VRM / MMD / GLB: voice, lip-syn…☆243Updated this week
- 面向长期运行与桌面协作的开源 AI Agent，提供常驻 Runtime、桌面 Agent、长期记忆与持续学习能力，可用于个人助理、自动化任务与本地工作流。☆1,033Updated this week
- ☆740Oct 14, 2026Updated 2 weeks ago
- 大模型驱动的npc决策，npc和玩家平权☆1,186Mar 29, 2026Updated 7 months ago
- MOMO CODE — RSI *JEV*Pi --AI coding agent that evolves with you☆1,107Updated this week
- 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.
- 一站式 Coding Agent 插件：从需求、研究、设计、原型到开发、测试、发布的全流程规则、Skills 与 Hooks，助力任何 0-1 的想法☆184Oct 11, 2026Updated 2 weeks ago
- 你的FLuent ai帮手☆79Aug 27, 2026Updated 2 months ago
- ☆477Updated this week
- 般若波罗蜜。回到每一个争吵和沉默的节点，看看另一个版本的结局。☆828Sep 17, 2026Updated last month
- ☆168Oct 12, 2026Updated 2 weeks ago
- MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端，用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上，不依赖任何远端服务。☆1,033Updated this week
- ☆270Aug 18, 2026Updated 2 months ago