You are viewing a plain text version of this content. The canonical link for it is here.
Posted to discuss-archive@tvm.apache.org by Puddingfjz via Apache TVM Discuss <no...@discuss.tvm.ai> on 2022/02/21 14:49:53 UTC
[Apache TVM Discuss] [Questions] Does tvm support dynamic input shape?
Hi, is there any update about the dynamic input shape support now? Thanks!
---
[Visit Topic](https://discuss.tvm.apache.org/t/does-tvm-support-dynamic-input-shape/11069/5) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/38cd1cfa5c0fd1bede23a5014f064fb08fd6bea8c476f2790290d645cba1d841).
[Apache TVM Discuss] [Questions] Does tvm support dynamic input shape?
Posted by Yuchen Jin via Apache TVM Discuss <no...@discuss.tvm.ai>.
Dietcode is not upstreamed yet afaik, cc @ziheng, @ArmageddonKnight.
We will add an LSTM demo with dynamic input shape to the Relax repo probably next month, we will keep you updated! :)
---
[Visit Topic](https://discuss.tvm.apache.org/t/does-tvm-support-dynamic-input-shape/11069/9) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/4aff6157b23ecb8a6bf8856d3a531eb8ca1f3a22acfdf304225a4a5d347217ac).
[Apache TVM Discuss] [Questions] Does tvm support dynamic input shape?
Posted by Puddingfjz via Apache TVM Discuss <no...@discuss.tvm.ai>.
Thanks for your quick reply!
Is the Dietcode work integrated into TVM now? Are there any examples to show how to use tvm to optimize dynamic input shape operators?
Is there examples of supporting LSTM or which part of code is related to this?
---
[Visit Topic](https://discuss.tvm.apache.org/t/does-tvm-support-dynamic-input-shape/11069/8) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/5af5d88863dd60805a87ff0f700ae07461ded3213086b004d694c03d38385364).
[Apache TVM Discuss] [Questions] Does tvm support dynamic input shape?
Posted by Yuchen Jin via Apache TVM Discuss <no...@discuss.tvm.ai>.
Hi @puddingfjz, we are working on Relax(Relay Next), which has first-class symbolic shape support. Here is a simple dynamic input shape [example](https://github.com/tlc-pack/relax/blob/relax/tests/python/relax/test_vm.py#L428-L448). Please check out the [overview](https://github.com/tlc-pack/relax/wiki/Relax-Architecture-Overview) of Relax and our [TVMCon talk](https://youtu.be/xVbkjJDMexo) for more information.
@ziheng has worked on dynamic-shape workload tuning: https://www.tvmcon.org/events/dietcode-automatic-optimization-for-dynamic-tensor-programs/.
@yongwww is working on supporting LSTM on Relax, and adding control flow support(e.g., closure, while_loop) to Relax.
---
[Visit Topic](https://discuss.tvm.apache.org/t/does-tvm-support-dynamic-input-shape/11069/6) to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/8520862ee6d60e8b87f93bcdd647a710d0982bd89f639fc0984ea4728fd713dc).