time-to-first-token
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
RÉPERTOIRE HYSEN LABS
Des dépôts sélectionnés avec une taxonomie précise, des métadonnées vérifiées et un contexte pratique.
A 10-week, 30-minutes-a-day roadmap for LLM inference serving and optimization. vLLM, SGLang, quantization, speculative decoding, benchmarking.
Use LLMs in Excel formulas
A real-time method that estimates the 3D human pose directly in the popular Bio Vision Hierarchy (BVH) format, given estimations of the 2D body joints originating from monocular color images. Our contributions include: (a) A novel and compact 2D pose NSRM representation. (b) A human body orientation classifier and an ensemble of orientation-tuned
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.
A useful plugin for the ChatGPT web platform, focusing on long conversation browsing, exporting, searching, prompt management, and timeline navigation. 🚀||优化ChatGPT长会话卡顿,聊天记录一键导出,消息搜索跳转,会话管理,prompt管理和时间线导航
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP
A structured 3-agent AI dev team — Architect, Builder, Reviewer. Built from production use. Token-optimized. Works with Claude Code, VS Code, Cursor, and any AI that supports context files.
“AI-Compass”将为社区指引在 AI 技术海洋中航行的方向,无论你是初学者还是进阶开发者,都能在这里找到通往 AI 各大方向的路径。旨在帮助开发者系统性地了解 AI 的核心概念、主流技术、前沿趋势,并通过实践掌握从理论到落地的全过程。
【影策】面向 AI 影视创作的开源无限画布工作台,集成多模态生成、分镜编排、素材管理与 Agent 工作流。
Web-based browser profile manager for CloakBrowser — create, launch, and manage isolated browser profiles with unique fingerprints. Free, self-hosted Multilogin alternative
Experimental DLSS Multi Frame Generation controls for any supported MFG title on RTX 40 series GPUs
AI-Native & Cloud-Native FS : une couche sémantique de fichiers hautes performances pour le stockage d'objets dans le cloud, intégrée à un cache haute vitesse. Projet bac à sable CNCF.
Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs
Official SGLang × Datawhale course on LLM inference (中英双语): understand inference, build a mini-sglang from scratch, then read the real SGLang source and land your first PR. 《从零手搓SGLang》:读懂推理,手搓 mini-sglang,吃透 SGLang 源码。
This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!
Self-paced bootcamp on Generative AI. Tutorials on ML fundamentals, Ollama, LLMs, RAGs, LangChain, LangGraph, Fine-tuning, DSPy & AI Agents (CrewAI), (Using ChatGPT, gpt-oss, Claude, Qwen, Gemma, Llama, Gemini)
Open-source task management for the agentic era. The command center for solo entrepreneurs who delegate work to AI agents.
A project converting the Qwen web page to an API.
Générateur d'applications IA open source et auto-hébergé, un agent crée de véritables applications dans des bacs à sable isolés sur votre propre serveur, chacun vivant sur une URL d'aperçu. Auto-hébergement en une seule commande. MIT.
A list of open-source AI projects you can use to generate income easily.