I found out that gtx1050, gtx3090 does not support the corresponding schedule
for cuda.
I think 20 series are needed (at lease gtx2080 does support).
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-tensorcore-int4-end-to-end-inference/7534/23)
to respond.
You are receiving this be
No problem. I think the GPU you ran on before doesn't have Tensor Core so the
TVM doesn't find the corresponding schedule to use.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-tensorcore-int4-end-to-end-inference/7534/22)
to respond.
You are receiving this because you enabled ma
I changed my gpu to gtx2080 and the problem is solved.. thanks anyways.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-tensorcore-int4-end-to-end-inference/7534/21)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
1.
[cpp_deploy](https://github.com/apache/tvm/blob/main/apps/howto_deploy/cpp_deploy.cc)
2.
[c_runtime_api.h](https://github.com/apache/tvm/blob/main/include/tvm/runtime/c_runtime_api.h)
3. [bundle_deploy](https://github.com/apache/tvm/tree/main/apps/bundle_deploy)
---
[Visit Topic](http
I know TVM can easily invoke a compiled kernel from Python.
I want to export the .o file and integrate it to a C/C++ binary.
Is there any existing SDK to do that? If not I am willing to contribute one.
---
[Visit Topic](https://discuss.tvm.apache.org/t/do-we-have-a-c-host/9687/1) to
respond
Good point. It's a lot more clear. I'll adopt in the PR.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/new-target-intrinsic-lowering-and-legalization-mechanism/9683/3)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
Thanks @giuseros I agree what you said about removing overheads for embedded.
In the meantime, it is also good to think about some form of standardization
specifically for embedded land that maintains the minimalism while still offers
some generality.
For example, some standardization aroun
