You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@tvm.apache.org by yangdeyu via TVM Discuss <no...@discuss.tvm.ai> on 2019/08/12 01:31:11 UTC

[TVM Discuss] [Development] Whether TVM will support dynamic shapes in the future


   I would like to know whether dynamic shapes are already supported in a planned way. I am not familiar with other deep learning frameworks, but without dynamic shapes, many OP of TF cannot be added, which leads to TVM's narrow choice of models and lack of generality.
  I seem to see some dynamic information in the recent PR, so if there is a plan, could anybodyplease tell me the approximate time?Thanks a lot for this.





---
[Visit Topic](https://discuss.tvm.ai/t/whether-tvm-will-support-dynamic-shapes-in-the-future/3700/1) to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/329871fd8417a04496990333a65e15cd0775e6c49339543d11eb962a3fc00c1a).

Tianqi Chen, UW, Seattle, WA, 98105, United States
http://tracking.discuss.tvm.ai/tracking/unsubscribe?msgid=2Ahnot6YQIhEGbdY-4SQbQ2