A GPU task manager for Windows, Linux, and WSL: per-process VRAM, GPU activity, and LLM model/KV-cache insights (Windows AMD and NVIDIA).
Python
Merge main into the bare-metal Linux NVIDIA live-check PR
Scott Hanselman511196e509ba
diff --cc AGENTS.mdindex feefd84,cd8e24c..352e9dc--- a/AGENTS.md+++ b/AGENTS.md@@@ -134,8 -138,10 +138,11 @@@ workflow `release.yml`, and environmen## Known limitsValidated live: Windows 11 with an RTX 4080 SUPER (WDDM, plus WSL2), a Linux container with an--RTX 3060 Ti, macOS 26.3.1 on an M4 Mac mini (Metal; own-user processes, not run as root), and-bare-metal Linux with an amdgpu Radeon RX 9070-series card plus a Radeon 610M (DRM path).++RTX 3060 Ti, macOS 26.3.1 on an M4 Mac mini (Metal; own-user processes, not run as root),+bare-metal Linux with an amdgpu Radeon RX 9070-series card plus a Radeon 610M (DRM path), and+bare-metal Linux on a laptop with an RTX 4050 Laptop GPU plus an AMD Phoenix iGPU (NVML and DRM side by side).- Not yet validated on hardware: systems with two discrete GPUs, multi-GPU on Windows, and GPU-backed WinML on- Copilot+ PCs. Planned work is listed under **Next** in the README.+ Intel i915 (an Arc A770 with resizable BAR plus a UHD 730) was validated by a contributor, not repeated by+ the maintainer.-Not yet validated on hardware: bare-metal Linux with NVIDIA, multi-GPU systems, Intel `xe` and Arc cards++Not yet validated on hardware: systems with two discrete GPUs, multi-GPU on Windows, Intel `xe` and Arc cards+ without resizable BAR, and GPU-backed WinML on Copilot+ PCs. Planned work is listed under **Next** in the+ README.diff --cc README.mdindex 21b5498,be560ba..b1f3a92--- a/README.md+++ b/README.md@@@ -850,7 -928,8 +940,8 @@@ downloads are bundled in this repositor- Model identity for non-GGUF runtimes (ONNX Runtime, PyTorch, TensorRT) beyond installed candidates.- Explicit provenance and availability for every counter and estimate.- Reliable multi-GPU matching and per-device model placement.- - Intel GPUs (`i915`/`xe`) through the same DRM fdinfo path as AMD.-- Bare-metal Linux validation on NVIDIA hardware; Intel `xe` per-process memory and load (`drm-cycles-*`), the Intel GT- clock in the device panel, and Intel validation beyond the Arc A770 / UHD 730 pair.++- Intel `xe` per-process memory and load (`drm-cycles-*`), the Intel GT clock in the device panel, and Intel++ validation beyond the Arc A770 / UHD 730 pair.- macOS: a portable build, Ollama/llama.cpp/MLX validation, and compressed GPU memory (footprint's`swapped`) as the paged column.- WSL: per-process GPU load for Linux rows, and Ollama's systemd journal as a log source.