File 002 · Local Intelligence
Record 096 · Runtimes · 2019
19.96.UDirectML
Microsoft
“A DirectX 12 ML path so AMD, Intel, and NVIDIA laptops can all run models.”
GPU inference on whatever Windows GPU you have.
DirectML (and the ONNX EP) is why a Windows box without CUDA can still host a local model. The compatibility GPU API.
Opened vendor-neutral Windows GPU inference.
Filed notes
- DX12 ML API
- ONNX Runtime EP
- Broad GPU coverage
SIC
7372
Prepackaged Software
NAICS
511210
Software Publishers
