Skip to content

ONNX improvements (-62% in full-precision model size, 2.7x faster load and execution, quantizations) #40

ONNX improvements (-62% in full-precision model size, 2.7x faster load and execution, quantizations)

ONNX improvements (-62% in full-precision model size, 2.7x faster load and execution, quantizations) #40

format-code

succeeded Feb 4, 2025 in 8s