Havuz

OpenLake, GPU tabanlı LLM inference ve training iş yükleri için dağıtık, kalıcı ve yüksek throughput hedefleyen bir storage engine'dir.

Neden yükseliyor · 154 günlük bir repo için 2.658 yıldız dikkat çekici; KV cache offload ve GPU kullanımını artırma gibi güncel, maliyetle doğrudan ilişkili bir altyapı sorununa odaklanıyor. Son 28 günde 16 commit var, ancak bunlar yalnızca 3 farklı yazardan geliyor. README'deki benchmark ve performans iddiaları proje tarafından yayımlanmış; verilen bilgiler bağımsız doğrulamayı göstermiyor.

tty7, oturumları uygulama kapandıktan sonra da sürdüren; shell, SSH ve coding agent iş akışlarını bir araya getiren Rust tabanlı bir terminal workbench’tir.

Neden yükseliyor · 83 günlük yaşına karşın 1124 yıldız ve son 28 günde 320 commit, projeye belirgin ilgi ve yoğun geliştirme olduğunu gösteriyor. README’deki persistent sessions, agent desteği ve SSH özelliklerini tek bir terminal workbench’te birleştirmesi de dikkat çekici; ancak son dönemdeki 4 farklı yazar, geliştirme etkinliğinin sınırlı sayıda kişide toplandığını gösteriyor.

A high-performance framework for training LLMs, VLMs, diffusion, and embodied models on NVIDIA GPUs and Kunlun XPUs. Supports Pi0.5, GR00T

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

SiliconScope, Apple Silicon Mac’lerde sistem kaynaklarını ve özel hızlandırıcıları izleyen, ayrıca uzaktaki makineleri aynı panele ekleyebilen bir macOS monitörüdür.

Neden yükseliyor · 111 günde 966 yıldıza ulaşması ve son 28 günde 48 commit alması dikkat çekiyor; README’deki ANE ve memory-bandwidth ölçümleriyle uzaktaki makineleri tek panelde toplama özellikleri de ayırt edici bir kullanım vaadi sunuyor. Üç farklı yazar aktiviteye işaret etse de ekip genişliği sınırlı; yıldızlar tek başına benimseme veya kalite kanıtı değil.

Run any local LLM engine, auto-tuned to your GPU — polished web UI + OpenAI/Anthropic-compatible API. Point Claude Code at your own machine

Real-time hardware and LLM inference monitoring — GPU, CPU, memory, and vLLM metrics streamed to a dashboard.

Realtime TUI monitor for local LLM servers (ollama, llama.cpp). The only GPU monitor that knows what model is running and how much each toke

collabosm, kullanıcının Google Colab hesabında GPU başlatıp Qwen3.8 modellerini yerel uygulama ve OpenAI uyumlu API üzerinden kullanmasını sağlar.

Neden yükseliyor · 3 günlük bir repoda 87 yıldız dikkat çekici bir başlangıç; ancak yıldızların neden geldiği ve kullanıcıların uygulamayı gerçekten çalıştırıp çalıştırmadığı mevcut verilerden anlaşılamıyor. Son 28 günlük commit ve farklı yazar ölçümleri de yok.

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

Self-hosted homelab dashboard in one container — GPU, local-AI VRAM, Docker, systemd, energy costs. Read-only MCP server so AI agents can ex

Turn any document or a whole zip into an interactive knowledge graph, using a self-hosted Qwen3.6-35B-A3B-MTP on a single NVIDIA L4

An open-source inference engine for AI functions in SQL

The Best TypeScript framework for fine-tuning

Run your AI agents on machines you already own, as one private P2P mesh. OpenAI-compatible, sandboxed with Podman, signed reputation, no clo

A GPU-rendered, terminal-first workspace: Agent framework, real shells, IDE, Markdown, and multiplayer — one Rust engine.

Fastest MoE/LLM inference runtime for consumer and edge Blackwell GPUs. SN74 on Gittensor.

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

Local AI agent sandbox runtime with Firecracker, gVisor, and NVIDIA GPU sandbox support.

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance

Self-hosted meeting transcription portal — speech-to-text, speaker diarization, LLM-corrected transcripts, structured summaries and Word min

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

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

Eve Agent V2 Unleashed — local-first autonomous AI coding agent powered by Ollama

A narrative walk through 90 years of AI history, paper by paper. 66 chapters from Turing 1936 to Blackwell 2025.

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

SpeakCrate: self-hosted text-to-speech API powered by Kokoro. OpenAI-compatible speech endpoint, 50+ voices across 9 languages, streamed aud

Unified KV-cache compression for LLM inference: 12 Python-native methods, guarded add-on composition and routing, analytical capacity simula

A free textbook on building an LLM inference stack from scratch in Rust.

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

Lynn 原生 LLM 推理引擎 · W4A8/NVFP4 量化 · 自写 CUDA/Triton kernel · MoE · 投机解码 | Lynn-native LLM inference engine for NVIDIA Blackwell

Your all-in-one funscript editor, generator, and player. Free tracking algorithms. A Pro Pass unlocks the next level AI generation right on

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → paralleli

The visual compute platform for AI and robotics — connecting agents, GPU workloads, simulation, training, and real robots through typed work

Persistent GPU jobs for AI agents. MCP + CLI, hardware-aware scheduling, Kaggle adapter, and recoverable artifacts for Codex and Claude Code

Which local LLMs can your computer run? Hardware-aware CLI, TUI and GUI: yes/slow/no verdicts and tok/s from your GPU VRAM and RAM, then ver

LLM Infra 工程实战 — 面向应用层工程师的 LLM 基础设施

MLOps — vLLM + LiteLLM + Portainer CE + Netdata. Case study song ngữ: kiến trúc, metrics, bài học vận hành. · Self-hosted LLM inference don

nvtop for vLLM — an interactive terminal dashboard for vLLM serving performance (concurrency, throughput, cache & KV memory, latency, spec-d

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

Profine automatically profiles and optimizes PyTorch training jobs on real GPUs, delivering measurable speedups and lower GPU costs before t

Grammar-aware adaptive speculative decoding for structured LLM output — custom CUDA/Triton kernels, 2.7× throughput on enum-heavy schemas

Benchmark llama.cpp on your own GPU/CPU boxes and compare against everyone else's — sweep runner, an sha256-keyed index of ~4M GGUF files, a

MCP server for NVIDIA GPU metrics give AI agents real-time access to GPU utilization, memory, temperature, and power

A self-hosted, AWS-compatible cloud for your own hardware. Point the AWS CLI, SDKs, CloudFormation and Terraform at it to run Lambda, S3, RD

ParseCrate: self-hosted document processing API powered by Docling and docling-serve. Converts PDF, DOCX, PPTX, HTML, and more to Markdown/J

The terminal your agent team lives in — run coding agents in panes on a shared bus, on a fast GPU-rendered terminal for macOS and Linux.

Kata builds the best AI agent for a subnet through open competition — so anyone can mine that subnet with a proven, optimized agent.

OpenAI-compatible multilingual TTS server — Chatterbox on vLLM with real-time PCM audio streaming, low time-to-first-byte (~0.7 s), voice cl

Native macOS terminal with GPU rendering, durable sessions, coding-agent workflows, and SSH connectivity. Session host, daemon, and CLI supp