[ARM] MatMulNBits Fp16 support - API change only - Githubissues

microsoft / onnxruntime

ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator

https://onnxruntime.ai

MIT License

14.77k stars 2.94k forks source link

[ARM] MatMulNBits Fp16 support - API change only #22826

Closed fajin-corp closed 1 week ago

fajin-corp commented 1 week ago

Description

A break-down PR of https://github.com/microsoft/onnxruntime/pull/22651 Op API change only.

add template to functions and classes that support fp32 and fp16
rename functions, classes and files that support fp32 and fp16 from SQNBxxx to QNBxxx

Motivation and Context