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.

All-in-one SSH/SFTP desktop client for GPU servers - built-in terminal, drag-and-drop file transfers, and live CPU/RAM/disk telemetry for NVIDIA, AMD, Intel, and Apple Silicon GPUs on Linux and macOS remotes. Tauri + React + Rust.

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

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.

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