Skip to content

ONNX improvements (-62% in full-precision model size, 2.7x faster load and execution, quantizations) #41

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) #41

Re-run triggered February 4, 2025 01:20
Status Success
Total duration 17s
Artifacts

main.yml

on: pull_request
format-code
8s
format-code
Fit to window
Zoom out
Zoom in