New pages
Jump to navigation
Jump to search
- 01:17, 4 February 2026 emmtrix ONNX-to-C Code Generator (hist | edit) [4,200 bytes] Timo.stripf (talk | contribs) (Created page with "'''emmtrix ONNX-to-C Code Generator (emx-onnx-cgen)''' is an emmtrix-developed '''AI frontend compiler''' that translates ONNX models into '''deterministic, analyzable C code''' specifically designed for '''auto-vectorization and embedded target optimization'''. The primary goal of emx-onnx-cgen is not to perform aggressive hardware-specific optimizations itself, but to generate '''high-quality C code''' that serves as an ideal input for the emmtrix '''Vectorizer''' and...") Tag: Visual edit
- 14:28, 30 January 2026 Numerical Precision in ONNX and AI Inference (hist | edit) [96,699 bytes] Timo.stripf (talk | contribs) (Created page with "= Numerical Precision in ONNX and AI Inference = == Introduction == '''Open Neural Network Exchange (ONNX)''' is an open standard format for representing machine learning models and neural network computations across different frameworks and hardware<sup>1(#ref-1)</sup>. As models are exported and deployed via ONNX, the '''numerical precision''' of computations becomes critical. Deep learning inference involves a variety of floating-point operations, and small nume...")