nvtop

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

AMD and NVIDIA GPUs htop like monitoring tool | Optimized builds

Digital-rain style htop/nvtop for NVIDIA GB10 (ASUS Ascent GX10, DGX Spark): GPU, unified memory and which AI models are loaded by vLLM, Ollama, ComfyUI & co.

NVIDIA GPUs htop like monitoring tool

Soft GPU reservation: a tiny CUDA process visible in nvidia-smi and nvtop

rockbottom (rb) — a Linux system monitor that actually reads the numbers for you and tells you what's wrong. Replaces htop, btop, top, nvtop.

A comprehensive system monitor for Linux desktops. It combines the depth of btop and nvtop, the process management of GNOME System Monitor, and the hardware inventory of inxi, behind one modern Qt interface.

Terminal dashboard for NVIDIA GPUs, system CPU/memory, and processes — clickable, with conda env / docker container / cwd info per process.

Java frontend to nvidia-smi monitoring

The htop & nvtop for Ollama, Local LLMs, GPUs, Databases and Batch Pipelines (Zero Dependencies)

lintop — real-time Linux system monitor for the terminal with NVIDIA, AMD and Intel GPU support (htop + nvtop alternative, written in Go)

Terminal session monitor for HAPI hubs - nvtop-style chart, sticky-cursor agent table, BBS-flavored TUI.

A Task Manager for the GPU on Windows: per-process VRAM (resident vs committed) + engine load. Treemap GUI, live TUI, JSON/NDJSON, MCP server, co-tenancy stamps for agents. C++20, zero deps, single exe.

View your GPU utilization, both for the total activity percent and individual blocks.

An nvtop for local LLM inference: zero-config autodiscovery of vLLM, llama.cpp, Ollama, TGI, SGLang + live GPU and serving metrics in a Textual TUI. Unified-memory (GB10/Jetson) aware. MIT.

btop-like monitoring for llm inference server and gpu stats across gpus/hosts

Terminal monitor for Hygon DCU (hy-smi) with nvtop-style scrolling curves