search

google-ai-edge / ai-edge-torch

Supporting PyTorch models with the Google AI Edge TFLite runtime.
Apache License 2.0
378 stars 51 forks source link

Request for tflite full int8 static quantization with calibration dataset #296

Open hayyaw opened 1 month ago

hayyaw commented 1 month ago

Description of the bug:

can not convert tinyllama to full int8 quantized tflite model

Actual vs expected behavior:

The compute platform only support int8 datatype, request for tflite full int8 static quantization with calibration dataset.

Any other information you'd like to share?

No response

pkgoogle commented 1 month ago

Noted.