LLM & Inference

Using Low-rank adaptation to quickly fine-tune diffusion models.

A MicroKernel Multi-Agents System Framework for Adaptive Social Simulation Powered by LLMs

A multi-agent research system for the humanities and social sciences.

An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.

MLNLP社区用来帮助大家论文Rebuttal的整理仓库。

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

Awesome Jev: a source-backed field guide to TypeSafe's System One model, with SDKs, live demos, agent tools, and independent evaluations.

A general fine-tuning kit geared toward image/video/audio diffusion models.

A curated list of tools built for Jev — TypeSafe AI's System One model for typed decisions.

List of software that allows searching the web with the assistance of AI: https://hf.co/spaces/felladrin/awesome-ai-web-search

从 NLP 到 LLM 的算法全栈教程，在线阅读地址：https://datawhalechina.github.io/base-llm/

OpenKB: Open LLM Knowledge Base

《大语言模型》作者：赵鑫，李军毅，周昆，唐天一，文继荣

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space

llama.cpp optimized for NVIDIA Tesla V100 (SM70). Qwen3.8-Flash-Next (MoE) with MTP on 1/2/3/6x V100-16GB at 262K context (6 GPUs: prefill 3402 tok/s at 200K; 2 GPUs on one socket: 2152 tok/s). Qwen3.8-27B with DFlash2 on 1-6 GPUs, up to 512K context. Multimodal, thinking, concurrent serving, built-in web UI.

Launch what you built on Jev, TypeSafe AI's System One decision model: a weekly board where makers launch and people vote, over an index of public Jev examples by decision pattern, with source citations, dated link checks and call-site text checks; runtime and performance are not independently tested here. EN/中文, JSON schema, platform matrix.

Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.

📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭代的知识体系。

LeaderWorkerSet & DisaggregatedSet: Kubernetes APIs for Distributed and Disaggregated AI Serving

Scout: the open-source browser agent, by Outcrawl. Mirrored automatically from Outcrawl's own repository.

[ACL 2026] Towards Efficient Large Language Model Serving: A Survey on System-Aware KV Cache Optimization

Connect your users to their apps

Build a ChatGPT like LLM from scratch in PyTorch, explained step by step.

微信聊天分析工具，支持本地 Laya 与 API 模型，提供意图识别、情绪感知、人物画像、群聊画像、好感度分析和 MBTI 聊天推测。

A simple, performant, and scalable Jax LLM!

🇨🇳 OpenClaw中文用例大全 | 50个真实场景 | 国内特色 + 海外案例的国内适配 | 自动化办公·内容创作·运维·AI助理·知识管理 | 新手友好

Strata Manager makes Niko1221/Strata, the local LLM inference engine, easier to set up and use. Manage local models and services, monitor hardware and API usage, chat and tune inference. Open-source desktop app for Windows / Linux x64.

AI论文系统 · AI论文生成、AI论文写作，一键论文生成，降AIGC、降重、答辩PPT · OEM白标招商加盟

JevChat-Windows：聊天窗口旁挂的回复辅助。窗口截图 + 本地离线 OCR 读对方消息 → Jev 判断意图 → 3 条候选一键填入，发送永远手动

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

A curated list of strategies, tools, papers, and resources for reducing LLM token costs and improving efficiency in production.

LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context

A model-agnostic GPU runtime for shipping models as verified programs.

AI 大模型世界，把 556 个大模型拟人化成像素小人的可视化站点。进来就能看到此刻谁最聪明、谁最会写代码、谁最便宜、谁刚发布，往下是国内与国外分区的厂商广场、完整的发布时间线和多维排行榜。搜索认模型名、厂商和能力，输入「多模态」会直接列出全部多模态模型。数据取自 Epoch AI、models.dev、LiveBench 与 Hugging Face，每小时自动同步，所有文案由真实数据生成，不调用任何 LLM。Next.js 静态导出，零后端。

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW classifier routing: 89% right note vs 62%, 2.1× faster ingest, 68% fewer tokens.

LuaN1aoAgent is a fully autonomous AI-driven penetration testing agent powered by graph-based cognitive reasoning.

“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。

The official implementation of Self-Play Fine-Tuning (SPIN)

[KDD'2026] "VideoRAG: Chat with Your Videos"

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

Pocket Flow: Codebase to Tutorial

A continuously-verified dataset of free-tier & trial-credit LLM APIs for developers. Every entry dated, sourced to the provider's own docs, and machine-readable. No hype, no dead links.

Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.

Make any NPC in any game talk back with Fish Audio: skills, a self-hosted voice server and tools for AI coding agents, with a full GTA V example.

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

🔥 A Survey on AI Auto-Research