gpu-server

You can run passively cooled single slot Tesla GPU/KI cards in a HP Proliant with a modified iLO ROM that take care of the fan and consequently temperature control.

Running large LLMs on pre-Ampere NVIDIA hardware — Tesla V100 (sm_70), RTX 2080 Ti (sm_75), CMP 170HX. Measured benchmarks, vLLM forks, and the hardware side: NVLink on SXM2 carrier boards, driver traps, cooling, used-kit acceptance.

Turn your high-end gaming PC or a friend's GPU laptop into a private AI cloud server accessible from anywhere. Zero-trust remote tunnels, drop-in local developer proxy for Claude Code & Cursor, and one-click orchestration for Ollama, ComfyUI, & 16+ AI tools.

GpuTerm – SSH/SFTP desktop client for GPU servers: terminal, file transfers and live CPU/RAM/disk/GPU telemetry (NVIDIA, AMD, Intel, Apple Silicon), plus an MCP server for AI assistants. Windows, macOS, Linux. Rust + Tauri + React.

Native macOS launcher for using DeepSeek Harness with remote models over SSH. ｜ 通过 SSH 让 DeepSeek Harness 使用远程模型的原生 macOS 启动器。

Аренда GPU-серверов по минутам: RTX 4090 от 25 ₽/ч, RTX 5090, A100, H100. Оплата СБП и криптой (USDT, TON). ComfyUI, Stable Diffusion, Ollama, генерация картинок без цензуры — gpu.nz

Open-hardware DIY AI/LLM server frame for 5-6 consumer GPUs (RTX 4090): 20x20 aluminium extrusion, SlimSAS PCIe risers, 19" 14U. STEP, STL, DXF, BOM, assembly guide.

A Spring Boot platform for managing Docker-based GPU workspaces and user approvals for KPSC

Run Claude Code backed by a self-hosted open-weight model (Qwen 3.5-35B) on AWS g6e — full setup guide, SSH tunnel, and benchmark scripts

EvE v2: two Tesla P4 GPUs on an HP ProDesk 600 G5 Mini over M.2-OCuLink, about $600. Build docs, photos, benchmarks.

Multimodal generative AI system for personalized children’s storybooks (Capstone Project, 2023)