comaniac commented on a change in pull request #9135:
URL: https://github.com/apache/tvm/pull/9135#discussion_r716871212
##########
File path: python/tvm/relay/frontend/pytorch.py
##########
@@ -3713,6 +3713,7 @@ def from_pytorch(
custom_convert_map=None,
default_dtype="float32",
use_parser_friendly_name=False,
+ return_int8_weight=False,
Review comment:
How about `keep_quantized_weight`? IIUC, this is effective when the
PyTorch model is already quantized. `return_int8_weight` might confuse users
and let them feel this flag can do quantization for them.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
