{"name":"gputaskman","repo":"shanselman/gputaskman","url":"https://midorreal.com/project/shanselman-gputaskman","repository":"https://github.com/shanselman/gputaskman","description":"A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM model/KV-cache insights for NVIDIA, AMD, and Intel GPUs (plus Huawei Ascend on Linux).","facts":{"license":{"value":"MIT","source":"https://github.com/shanselman/gputaskman","checked":"22 Nov 2026"},"language":{"value":"Python","source":"https://github.com/shanselman/gputaskman","checked":"22 Nov 2026"},"last_release":{"value":"v0.4.4, 17 Nov 2026","source":"https://github.com/shanselman/gputaskman/releases","checked":"22 Nov 2026"},"releases":{"value":"13","source":"https://github.com/shanselman/gputaskman/releases","checked":"20 Nov 2026"},"contributors":{"value":"23","source":"https://github.com/shanselman/gputaskman/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/shanselman/gputaskman","checked":"22 Nov 2026"}},"stars":3677.0,"writeup":{"what_it_is":"gputaskman is a terminal task manager for GPUs on Windows, Linux, WSL, and macOS on Apple Silicon. It shows per-process GPU memory and engine activity, and it identifies loaded runtimes, model files, and LLM buffer breakdowns such as weights, KV cache, and compute buffers.","audience":"Developers and users monitoring local GPU workloads such as LLM inference and training","claims":[{"kind":"specific","claim":"Shows per-process GPU memory and engine activity","excerpt":"A terminal UI that connects per-process GPU memory and engine activity with loaded runtimes, model files, and LLM buffer breakdowns.","status":"not_checked"},{"kind":"specific","claim":"Runs on Windows, Linux, WSL, and macOS on Apple Silicon","excerpt":"Windows + NVIDIA/AMD, with Linux and WSL support (NVIDIA everywhere, AMD on native Linux","status":"not_checked"},{"kind":"specific","claim":"Installable from PyPI with uv or pipx","excerpt":"uv tool install gputaskman","status":"not_checked"},{"kind":"specific","claim":"Provides a portable Windows download that needs no Python","excerpt":"No Python, uv, CUDA Toolkit, model download, or installation is needed.","status":"not_checked"},{"kind":"broad","claim":"Described as easy to use","excerpt":"**That's it.** uv obtains the pinned Python version if needed","status":"too_broad"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-08"},"why_now":null,"owner_supplied":null,"score":{"verdict":"real","hype":74,"reality":81,"gap":-8,"momentum":null,"confidence":85,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-11-17T21:43:57+00:00","text":"Latest release v0.4.4","source":"https://github.com/shanselman/gputaskman/releases"},{"date":"2026-11-03T04:19:23+00:00","text":"First release","source":"https://github.com/shanselman/gputaskman/releases"},{"date":"2026-11-03T00:49:34+00:00","text":"Repository created","source":"https://github.com/shanselman/gputaskman"}],"cite":"gputaskman is a GitHub project at https://github.com/shanselman/gputaskman written mainly in Python, described there as \"A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM model/KV-cache insights for NVIDIA, AMD, and Intel GPUs (plus Huawei Ascend on Linux)\".","attribution":"Data from Mid or Real, https://midorreal.com/project/shanselman-gputaskman, checked 22 November 2026. Attribution with a link is required.","still_real":null}