TUI that diagnoses AI training and inference GPU bottlenecks (VRAM, PCIe, offload).
-
Updated
Aug 15, 2026 - Python
#
nvml
Here are 116 public repositories matching this topic...
The GPU flight recorder — a cross-vendor GPU monitor that keeps persistent per-process history and a narrated event log just by being open. Your run stalled at 02:14 and you were asleep; scroll back and read why.
8000
rust cli machine-learning terminal monitoring time-series amd gpu intel tui nvidia nvml observability gpu-monitoring apple-silicon ratatui
-
Updated
Aug 16, 2026 - Rust
NVIDIA GPU management (clocks, voltage, fans) via NVML
-
Updated
Jul 1, 2026 - Rust
⚡ Open-source energy dashboard for your machine — real CPU/GPU/network watts, an optimizer that names the watts you can reclaim, and a telemetry-grounded copilot. Never fabricates a number: every metric is badged measured/estimated/simulated.
docker sustainability gpu nvml observability rapl energy-efficiency green-computing energy-monitoring fastapi apple-silicon powermetrics
-
Updated
Aug 19, 2026 - Python
Transparent library for CUDA/NVML that virtualizes GPU access, enforces memory limits, and enables container-friendly sharing with minimal performance overhead.
-
Updated
Apr 8, 2026 - C++
Python 3 Bindings for the NVIDIA Management Library
-
Updated
Jan 1, 2024 - Python
Per-process GPU memory, load, temperature and clock for Windows, with an overlay you can pin over a game.
windows csharp dotnet gpu winforms overlay hud nvml system-monitor performance-counters gpu-monitoring vram
-
Updated
Aug 11, 2026 - C#
Operations console for local LLM inference on constrained GPUs — per-card VRAM headroom, CUDA/NVML device-order reconciliation, and GGUF quant analysis before you download. Not a chat UI.
react python cuda self-hosted nvidia nvml quantization gpu-monitoring vram fastapi llm llama-cpp local-llm llm-inference gguf
-
Updated
Aug 27, 2026 - Python
Terminal GPU history monitor for NVIDIA, AMDGPU, and Apple Silicon
macos linux rust cli terminal monitoring gpu tui nvidia nvml nvidia-smi amdgpu system-monitor gpu-monitoring terminal-ui egui gpu-metrics apple-silicon gpu-monitor ratatui
-
Updated
May 18, 2026 - Rust
Your machine's personal assistant — DL-workload-aware system monitor (TUI)
-
Updated
Jun 17, 2026 - Python
Reproducibility-oriented benchmarking framework for CPU and accelerator workloads. Two-host: cpu (Intel + iGPU) and cuda (NVIDIA) profiles. RAPL/NVML energy, randomized execution, bootstrap CIs, Mann-Whitney comparison.
-
Updated
May 5, 2026 - Python
Сколько ватт съедает твой ПК прямо сейчас и во что это выльется за сутки. Консольный измеритель энергопотребления с TUI для Windows и Linux.
python windows linux cli energy-monitor tui nvml electricity rich pyinstaller power-consumption watts psutil rapl system-monitor hardware-monitoring
-
Updated
Aug 24, 2026 - Python
A local NVIDIA/NVML GPU monitoring dashboard with real-time charts, diagnostics, and demo mode.
-
Updated
May 25, 2026 - Python
MCP server that lets AI agents share one NVIDIA GPU — cross-session model claims, real busy detection via NVML, protected eviction, and full VRAM visibility for Ollama + everything else holding memory
-
Updated
Jul 29, 2026 - Python
Improve this page
Add a description, image, and links to the nvml topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the nvml topic, visit your repo's landing page and select "manage topics."