AI Infrastructure

MemPalace/mempalace

The best-benchmarked open-source AI memory system. And it's free.

Wei-Shaw/sub2api

Sub2API 一站式开源中转服务，让 Claude、Openai 、Gemini、Grok订阅统一接入，支持拼车共享，更高效分摊成本，原生工具无缝使用。

supabase/supabase

The Postgres development platform. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.

rohitg00/ai-engineering-from-scratch

Learn AI Engineering! Learn it. Build it. Ship it for others.

mudler/LocalAI

LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.

rustdesk/rustdesk

An open-source remote desktop application designed for self-hosting, as an alternative to TeamViewer.

CloakHQ/CloakBrowser

Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 50+ tests passed.

alibaba/nacos

an easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.

ruvnet/RuView

π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.

deepspeedai/DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

1Panel-dev/1Panel

🔥 1Panel is a modern, open-source Linux server management panel and a lightweight AI management platform.

hpcaitech/ColossalAI

Making large AI models cheaper, faster and more accessible

netdata/netdata

The fastest path to AI-powered full stack observability, even for lean teams.

MakazhanAlpamys/Soup

Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.

nocodb/nocodb

🔥 🔥 🔥 A Free & Self-hostable Airtable Alternative

firecrawl/firecrawl

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

Dokploy/dokploy

Open Source Alternative to Vercel, Netlify and Heroku.

ray-project/ray

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

amruthpillai/reactive-resume

A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!

novuhq/novu

The open-source communication infrastructure for agents and products

zeromicro/go-zero

A cloud-native Go microservices framework with cli tool for productivity.

facebook/rocksdb

A library that provides an embeddable, persistent key-value store for fast storage.

HeyPuter/puter

🌐 The Internet Computer! Free, Open-Source, and Self-Hostable.

microsoft/markitdown

Python tool for converting files and office documents to Markdown.

Kong/kong

🦍 The API and AI Gateway

tw93/Pake

Turn any website into a lightweight desktop app with one command, on macOS, Windows and Linux.

alibaba/arthas

Alibaba Java Diagnostic Tool Arthas/Alibaba Java诊断利器Arthas

meilisearch/meilisearch

A lightning-fast search engine API bringing AI-powered hybrid search to your sites and applications.

D4Vinci/Scrapling

🕷️ A Web Scraping framework that handles everything from a single request to a full-scale crawl! Don't be shy, join here: https://discord.gg/EMgGbDceNQ and follow here for daily tips and tricks: https

Fincept-Corporation/FinceptTerminal

FinceptTerminal is a modern finance application offering advanced market analytics, investment research, and economic data tools, designed for interactive exploration and data-driven decision-making i

openlake-project/openlake

OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

FareedKhan-dev/kimi-k3-in-c

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

pbatard/rufus

The Reliable USB Formatting Utility

gpustack/gpustack

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

daytonaio/daytona

Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code

buxuku/SmartSub

视频转字幕、字幕翻译、AI 配音与声音克隆、字幕烧录——免费开源的一站式桌面工具。基于 Whisper / FunASR 等本地模型离线语音转文字，批量处理 + 全平台 GPU 加速，跨 Windows / macOS / Linux。Free, open-source desktop app to generate, translate, dub & burn video subtitles —

chatanywhere/GPT_API_free

免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！

mouredev/Hello-Python

Curso para aprender el lenguaje de programación Python desde cero y para principiantes. 100 clases, 44 horas en vídeo, código, proyectos y grupo de chat. Fundamentos, frontend, backend, testing, IA...

transformerlab/transformerlab-app

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

labmlai/annotated_deep_learning_paper_implementations

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(

GokuMohandas/Made-With-ML

Learn how to develop, deploy and iterate on production-grade ML applications.

infinispan/infinispan

Infinispan is an open source data grid platform and highly scalable NoSQL cloud data store.

Michael-A-Kuykendall/shimmy

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

openvinotoolkit/nncf

Neural Network Compression Framework for enhanced OpenVINO™ inference

kitops-ml/kitops

An open source DevOps tool from the CNCF for packaging and versioning AI/ML models, datasets, code, and configuration into an OCI Artifact.

qdrant/qdrant-client

Python client for Qdrant vector search engine

LC044/WeChatMsg

loco-3d/crocoddyl

Crocoddyl is an optimal control library for robot control under contact sequence. Its solver is based on various efficient Differential Dynamic Programming (DDP)-like algorithms

beam-cloud/beta9

Ultrafast serverless GPU inference, sandboxes, and background jobs

SeldonIO/MLServer

An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more

utkuozdemir/nvidia_gpu_exporter

Nvidia GPU exporter for prometheus using nvidia-smi binary OR using NVML

volcano-sh/kthena

Kubernetes-native AI serving platform for scalable model serving.

StarlightSearch/EmbedAnything

Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust 🦀

FedML-AI/FedML

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs on a

brian-team/brian2

Brian is a free, open source simulator for spiking neural networks.

GradientHQ/parallax

Parallax is a distributed model serving framework that lets you build your own AI cluster anywhere

sysprog21/shecc

A self-hosting and educational C optimizing compiler

Malix-Labs/Awesome-Atomic

An awesome curated knowledge-base about atomic systems

NGT-labs/NGT

Nearest Neighbor Search with Neighborhood Graph and Tree for High-dimensional Data

DaoyuanLi2816/can-i-finetune-this

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

hanruihua/ir-sim

A Python-based lightweight robot simulator designed for navigation, control, and learning

mosecorg/mosec

A high-performance ML model serving framework, offers dynamic batching and CPU/GPU pipelines to fully exploit your compute machine

giannisanni/pulsar

SSD-streaming inference engine for giant MoE models (Rust + CUDA). GLM 5.2 743B at 2 tok/s and Hy3 295B at 7 tok/s on two consumer 16GB GPUs. Zero-config multi-GPU: measures PCIe bandwidth, places att

hasso5703/dgx-spark-qwen38

Fastest measured Qwen3.8-27B config for DGX Spark (GB10): SGLang + NVFP4 + DFlash2, 71.4 tok/s greedy median, 1M context, deterministic boots. Flash-Next 176B on one box. One command, everything pinne

Tencent/TurboTransformers

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

kamalkraj/BERT-NER

Pytorch-Named-Entity-Recognition-with-BERT

NVIDIA/nvcf

Platform for deploying and routing GPU-accelerated inference, streaming, and batch workloads at scale.

ELS-RD/transformer-deploy

Efficient, scalable and enterprise-grade CPU/GPU inference server for 🤗 Hugging Face transformer models 🚀

beehive-lab/GPULlama3.java

GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

huawei-noah/Efficient-Computing

Efficient computing methods developed by Huawei Noah's Ark Lab

FenTechSolutions/CausalDiscoveryToolbox

Package for causal inference in graphs and in the pairwise settings. Tools for graph structure recovery and dependencies are included.

grafbase/grafbase

[Acquired by The Guild] The Grafbase GraphQL Federation Gateway

Toni-SM/skrl

Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, MuJoCo Playground and other environments

Tencent/TencentPretrain

Tencent Pre-training framework in PyTorch & Pre-trained Model Zoo

pmady/keda-gpu-scaler

KEDA External gRPC Scaler for GPU workloads - native NVML metrics via DaemonSet, no Prometheus required

jmerelnyc/Talos

GPU worker client for the Talos network. Pairs with your Talos account, serves open-model inference jobs over a WebSocket, and reports uptime for payouts.

Prismer-AI/PrismerCloud

Prismer Cloud

dreddnafious/thereisnospoon

A machine learning primer built from first principles. For engineers who want to reason about ML systems the way they reason about software systems.

raketenkater/ggrun

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

AntSeed/antseed

AntSeed P2P AI Network - An open market for AI inference. No gatekeepers.

NVlabs/QeRL

[ICLR 2026]QeRL enables RL for 32B LLMs on a single H100 GPU.

run-house/kubetorch

Distribute and run AI workloads on Kubernetes magically in Python, like PyTorch for ML infra.

ebhy/budgetml

Deploy a ML inference service on a budget in less than 10 lines of code.

amun-ai/hypha

A distributed application framework for large-scale data management and AI model serving

luyug/GradCache

Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint

zeokin/Cuda-Compute-OSS

CCO is an open-source system for managing, validating, and improving GPU.

bjk110/spark_vllm_docker

DGX Spark / GB10 vLLM Docker stack for large-model serving, presets, patches, and validation notes.

aivrar/multi-turboquant

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simulation, Godzilla KVarN/TriAttention with SM86/SM89 qualificati

Lair-ai/lair

Private AI framework

arizqi/cpubrrr

Frontier-class LLM inference on a laptop CPU — gpt-oss:20b at ~110 tok/s on Apple M4 Max, 7.5x llama.cpp, no GPU. From-scratch NEON/SME kernels in Rust.

ROCm/rocm-cli

ROCm CLI is a command-line tool for setting up and running local AI on AMD GPUs, with a full-screen TUI dashboard for GPU telemetry, model serving, and chat.

zhouzhupianbei/UAV-Stack-Knowledge-Base

无人机（UAV）领域的“百科全书”。本项目深度整合了无人机**政策解读、硬件选型、通讯协议（MAVLink/SDK）、边缘计算（YOLO/AI）、流媒体分发（ZLMediaKit）及 GIS 可视化（Cesium）**的全链路知识。

guilt/TinyToT

TinyToT — Tree of Thoughts inference server

getainode/ainode

Turn any NVIDIA GPU into a local AI platform. Inference + fine-tuning in your browser. One command to start, automatic clustering.

skaggsxyz/moltstream

Agent-native streaming infrastructure. The streaming runtime built for non-human broadcasters.

undeemed/kimi-k3-in-rust

CPU inference for Kimi K3, a 2.78T-parameter MoE LLM, in pure Rust. No GPU, no BLAS, no PyTorch. Streams the checkpoint from disk. Byte-identical port of kimi-k3-in-c.

ScilifelabDataCentre/serve

SciLifeLab Serve is a platform offering machine learning model serving, data science app hosting (Shiny, Gradio, Streamlit, Dash, etc.), and other tools to life science researchers affiliated with a S

benedekrozemberczki/GraRep

A SciPy implementation of "GraRep: Learning Graph Representations with Global Structural Information" (WWW 2015).

gogluejf/rig-stack

Turn your GPU into a managed private AI cloud.

atomicmilkshake/llama-cpp-turboquant

llama.cpp fork with TurboQuant quantization (turbo2/3/4) and TriAttention GPU-accelerated KV cache pruning. 75 tok/s on Qwen3-8B / RTX 3080.

MacPaw/macapptree

Repository for macos accessibility parser

1bit-MONSTER/1bit-MONSTER

Model-agnostic, hardware-agnostic pure-C++ inference engine — one binary, NPU + GPU + CPU. 94% HF architecture coverage. Reverse-engineered AMD's closed-source Strix Halo NPU stack in 4 days. GGUF/ONN

LostBeard/SpawnDev.ILGPU.ML

Hardware-agnostic machine learning infrastructure for .NET. Implements high-performance neural network layers in C# that are transpiled to run on WebGPU, CUDA, OpenCL, WebGL, CPU, and Wasm via SpawnDe

youngharold/tightwad

Mixed-vendor GPU inference cluster manager with speculative decoding

arkorlab/haru

GPU orchestrator with vLLM sleep mode

bhimrazy/litserve-examples

LitServe Examples ⚡ | This repository contains a collection of example applications built using LitServe, a high-performance AI model serving engine.

hanxiao/Qwen3.6-35B-A3B-MTP-L4

Deploy Qwen3.6-35B-A3B (Q4_K_XL) + MTP speculative decoding on a single NVIDIA L4 24GB — GCP g2-standard-8 — via the official llama.cpp Docker image. Decode-optimized to ~91–99 tok/s (min ~91 chat, ma

merely-made/wgpu-graft

Library for embedding native GPU textures (GL FBO, Vulkan image, Metal IOSurface) into wgpu textures.

DaoyuanLi2816/llm-gpu-lab

One GPU. Full LLM workflow. Real benchmarks. No cloud required.

RegiaYoung/SlideFormer

An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU (DAC ‘26)

thebasedcapital/ane-infer

Apple Neural Engine (ANE) LLM inference engine — reverse-engineered private APIs, Metal GPU shaders, hybrid ANE+GPU+CPU on Apple Silicon. 32 tok/s matching llama.cpp, 3.6 TFLOPS fused ANE mega-kernels

Aaryan-Kapoor/ModelGate-Hackathon

🏆Winning Project | ModelGate is a contract-aware AI control plane that ingests customer contracts, extracts SLA/privacy/routing constraints, and generates an OpenAI-compatible endpoint that automatica

e1n00r/tinyserve

30 tok/s for 20B MoE on 8 GB VRAM. Flat throughput to 32K context. Native MXFP4 + GGUF Q4_K/Q5_K/Q6_K via ggml CUDA kernels — zero dequant. Expert offloading for models that don't fit in GPU memory.

Brack-Wang/finetune_omega

Omega-Forge: unofficial code to finetune or train VGGT-Omega (VGGT-Ω) on your own dataset, for use while official training code is not yet available. Additionally includes a standalone zero-GPU 3D rec

PureBee/purebee

A GPU defined in software. Runs Llama 3.2 1B at 3.6 tok/sec. Zero dependencies.

PuxHocDL/m-gpux

Professional CLI toolkit for Modal GPU workflows, Docker Compose deployments, Python runtimes, model serving, and account/billing management.

mts-ai/OpenAutoNLU

An open-source pipeline for training natural language understanding models

latenceainew/colsearch

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and

Dosi-f/synthforge

🧪 SynthForge — toolkit for generating high-quality synthetic datasets for LLM fine-tuning. Multi-backend, filterable, GPU-accelerated. Early-stage experimental project.

dreadnode/tensor-man

A utility to inspect, validate, sign and verify machine learning model files.

NetraRuntime/sam3.c

Efficient SAM3 (Segment Anything Model 3) inference from scratch in pure C — Metal GPU + multithreaded CPU, no Python dependencies

ArgentAIOS/dgx-spark-cluster

Complete setup guide for a 2-node NVIDIA DGX Spark cluster — distributed training, CUDA inference with EXO, NCCL tuning for Grace Blackwell, NVMe-TCP shared storage, and 200 Gb/s direct fabric network

SuleynanAuir/Distributed-Fine-Tuning-of-Qwen2.5-7B-as-HotelService-Master

Hotel-domain conversational assistant using Qwen2.5-7B-Instruct, focusing on practical, reproducible fine-tuning. It supports SFT + LoRA for a stable baseline, SFT + QLoRA for 7B model training with 4

Kuddev/pebrel

AI-native, GPU-accelerated terminal emulator for Windows with SSH, persistent sessions, split panes, and first-class AI CLI workflows.

aigrantsindia/aigrantsindia

The non profit fostering AI in India through credits, grants, resources

ovg-project/kvcached

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

amitshekhariitbhu/llm-internals

Learn LLM internals step by step - from tokenization to attention to inference optimization.

autonomous-ai/Personal-AI-Computer

Open-source AI computer designs, from desktop workstations to 8-GPU servers.

apple/ml-aim

This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

EvanZhouDev/openai-oauth

Free AI with your ChatGPT account

Willxup/cpa-usage-keeper

Standalone CliProxyAPI usage tracker with SQLite persistence and built-in dashboard.

Xilinx/embeddedsw

Xilinx Embedded Software (embeddedsw) Development

AvenCores/open-antigravity-patcher

🔑 Патчер Antigravity для снятия региональных ограничений 🔓

flagos-ai/FlagGems

FlagGems is an operator library for large language models implemented in the Triton Language.

Geekgineer/YOLOs-CPP

Cross-Platform Production-ready C++ inference engine for YOLO models (v5-v12, YOLO26). Unified API for detection, segmentation, pose estimation, OBB, and classification. Built on ONNX Runtime and Open

mw00/project-maya

Project Maya - run GLM-5.3-Flash (321B MoE) privately on your own GPU(s), from one card to 16, NVIDIA or AMD, Linux or Windows. Engine, server, dashboard, OpenAI- and Anthropic-compatible API, quant t

timoncool/YuE2-Studio

Local AI song generator with an editable score — YuE2 on your GPU: full songs with vocals, sheet music, covers, exact replay. Native Windows app, no Python, installer with auto-update.

peters/horizon

GPU-accelerated terminal board that puts all your sessions on an infinite canvas

micytao/vllm-playground

A modern web interface for managing and interacting with vLLM servers (www.github.com/vllm-project/vllm). Supports both GPU and CPU modes, with special optimizations for macOS Apple Silicon and enterp

prabanta-dev/janas

37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your

timoncool/ACE-Step-Studio

Portable AI music generator — full songs with vocals, covers, music videos. One-click install, 100% offline, NVIDIA GPU.

DaoyuanLi2816/mini-verl

verl for a single consumer GPU. PPO, GRPO and on-policy distillation on NVIDIA GPUs.

surya-koritala/Glyd

Lossless AI compression: 33% less GPU memory, bit for bit.

shtjww/llm-inference-capacity-handbook

大模型推理案头手册（开源版）：给定 GPU 算力，一个模型能扛多少 QPS？三层模型 × 三面墙 × 排队论 × 开环压测

MetaX-MACA/vLLM-metax

Community maintained hardware plugin for vLLM on MetaX GPU

cgtuebingen/ggnn

GGNN: State of the Art Graph-based GPU Nearest Neighbor Search

jpezzulli/sglang-rtxpro6000

Optimized SGLang runtime for Qwen3.8-27B FP8 with DFlash2 and Qwen3.8 Flash-Next NVFP4 with FR-Spec on one NVIDIA RTX PRO 6000 Blackwell 96 GB GPU (SM120): 524K context, HiCache and NIXL.

sudoingX/local-ai-on-your-gaming-gpu

run a 27b local ai on your gaming gpu, rtx 3060 and up, radeon rx 6600 and up in beta, 8gb or more, linux and windows, one line to install

Liu-Bot24/chatgpt-route-inspector

ChatGPT 模型路由检测器：查看服务器报告的真实响应模型，自动识别路由降级，GPT Pro 计划降智查询。｜ChatGPT Model Route Inspector: view the actual response model reported by the server, automatically detect routing downgrades, and check whether

VecSzn/lobes

An experimental local AI runtime. It relays one request through five small models with one job each, on a single 8 GB consumer GPU.

WecoAI/weco-cli

Production-Grade Autoresearch. Ideal for agent harness engineering, prompt engineering, ML model development, GPU kernels, and other optimizable code.

pegainfer-project/kern

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

AbrahamPaulJ/facefusion-mobile

FaceFusion for Android. Offline face swap running on the phone's NPU, GPU or CPU. Qualcomm Hexagon (v68 to v81), Vulkan fallback, no server and no upload.

NoizAI/YuE2-Turbo

Fast, concurrent inference for YuE2. Same model and recipe: 1.68× faster per song, 3.31× more songs per GPU.

laolaoshiren/ai-hot

🔥 AI热榜：面向中文用户的 AI 工具、模型、Agent、新闻导航站，GitHub + 网站双向信息流，每6小时自动更新

vllm-project/vllm-xpu-kernels

The vLLM XPU kernels for Intel GPU

xigh/open-weight-models

Curated list of open-weight AI models with commercially exploitable licenses, verified benchmarks, and no EU restrictions.

tinyBigGAMES/VindexLLM

VindexLLM is a pure Delphi, GPU-powered LLM inference engine that uses Vulkan compute shaders to run GGUF models entirely on the GPU. It performs full transformer inference without relying on Python,

The-School-of-AI/LLM

LightningLM 0.1V — Reference training pipeline for the LightningLM family. 2B dense seed → 5B MoE → 9B MoE → 120B sparse MoE through TurboQuant-PreTraining on a single eight-GPU node. Companion code f

ai-dynamo/snapshot

Snapshot gets GPU pods ready in seconds instead of minutes — by restoring a fully initialized GPU worker instead of starting one from scratch. Kubernetes-native checkpoint & restore that runs alongsid

lirantal/tokenu

a unix-like du command line tool to count token usage per files and directories

Snowflake-AI-Research/Arctic-Platform

Arctic Training and Inference Platform

jceronch1/Clonar-voz

Clonación de voz y texto a voz 100% local con Qwen3-TTS y llama.cpp. Funciona en CPU y GPU, 10 idiomas, interfaz web en español.

Jwuthri/SelfJev

Open decisions model with Jev's API: typed answers (yes/no, choice, score, multi) with probabilities from forward passes, no generation. Qwen3.5-4B + LoRA, one GPU.

hugalafutro/model-hotel

Multi-Provider AI Gateway - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and more - "Because we have LiteLLM at home"

Leb947/modernbert-multi-task-studio

ModernBERT Multi-Task Fine-Tuning Hub 2026: Streamlined AI Workflows

neminov4030034/logfire-trainer-trace

Logfire ML Training Insights: 2026 AI Observability & Transformers Callback Monitoring

AbdelStark/attnres

Rust implementation of Attention Residuals from MoonshotAI/Kimi

igrbible/Ruach_Studio

A full music studio and WebUI for YuE2. Score first (ABC/MIDI), LoRA training, stems, remaster, upscale, lyrics check, DAW export. Songs from words on your own GPU. yue2.cpp · 7 languages · OSEM: Open

jaeseok614/ai-hardware-fit

Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.

sultaniman/wetron

wetron is a browser-based neural network model visualizer. Open a model and explore its computation graph interactively.

machaao/llama-net

Turn any Mac or GPU into an OpenAI-compatible inference node. One-command setup, automatic HTTPS, model management, and distributed request routing.

ur-grue/toptop

The local-inference observability layer for your terminal: live tokens/sec, VRAM-spill & throttle warnings, the GPU metrics nvidia-smi can't show. Also a gorgeous htop/btop-class system monitor. Rust

ddickmann/colsearch

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and