Feingranulare Post-Training-Quantisierung für die Hardwarebeschleunigung Künstlicher Intelligenz mit Gemischter Präzision
Anmelder: Microsoft Technology Licensing, LLC 🇺🇸
Details
- Veröffentlichungs-Nr.
- EP4822601
- Anmeldetag
- 25. März 2026
- Veröffentlichung
- 14. Oktober 2026
- Rechtsraum
- EP
Abstract
A method for recommending a mixed-precision data type configuration to accelerate execution of a language model includes identifying a plurality of mixed-precision test configurations that assign mixed-precision data types among components of the language model; measuring saliency metrics for the language model while the language model is executed in a test environment configured in accord with multiple of the plurality of mixed-precision test configurations; generating a saliency ranking that ranks the components based on the saliency metrics; and generating the recommended mixed-precision data type configuration. The recommended mixed-precision data type configuration assigns a first, reduced-precision data type to a least salient subset of the components identified in the saliency ranking while assigning a second, higher-precision data type to a most salient subset of the components identified in the saliency ranking.
Anmelder
- Firma
- Microsoft Technology Licensing, LLC
- Land
- 🇺🇸 USA
US-amerikanisches Technologieunternehmen mit Sitz in Redmond, Washington, gegründet 1975. Entwickelt Betriebssysteme, Software, Cloud-Dienste und Hardware, darunter Windows, Office und Azure.
25.226 Patente in unserer Datenbank