[Apache TVM Discuss] [Questions] Are web or webassembly supported autotvm

I've already build websocket demo, and run our model with web assembly backend in browser. but kernel is not tuned with this machine. I've read some tutorials about android、cuda etc. I found rpc tracker is usefull. Do we another way without rpc tracker that could be able to do tuning in bro

[Apache TVM Discuss] [Questions] Heterogeneous execution on TVM with custom accelerator

Thanks @max1996 ! Somehow missed/overlooked this. Looks very promising. --- [Visit Topic](https://discuss.tvm.apache.org/t/heterogeneous-execution-on-tvm-with-custom-accelerator/9557/3) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these e

[Apache TVM Discuss] [Questions] Feedback on TVM port to custom accelerator

Hi @JosseVanDelm , Thanks for the post! Some thoughts: >Right now a lot of calls to the HWlib are very inefficient, as they require a >lot of data reformatting on the RISC-V before being accessible to the >accelerator. It is weird/annoying that the data layout already gets specified >from Re

[Apache TVM Discuss] [Questions] Print out schedule for debugging

Is it possible now to get the above "schedule" representation? --- [Visit Topic](https://discuss.tvm.apache.org/t/print-out-schedule-for-debugging/1885/7) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://dis

[Apache TVM Discuss] [Questions] TVM and custom accelerators

hi @dream-math @jossevandelm @Julien Thanks for some great collaboration, seems like there is significant community interest in merging RISC-V support. Let's lay out some steps we can follow to make this happen, and then we can discuss timelines. 1. To start with, I propose we explicitly tes

[Apache TVM Discuss] [Questions] Does AutoTvm check correctness of tuning results?

AutoTVM has an option to check the correctness in the past but has been removed recently due to various of reasons. See the following PR for details https://github.com/apache/tvm/pull/7250 --- [Visit Topic](https://discuss.tvm.apache.org/t/does-autotvm-check-correctness-of-tuning-results/

[Apache TVM Discuss] [Questions] TVM and custom accelerators

hi @Julien , With the help of @areusch , I have tried to make `tvm/tests/micro/qemu` work on `qemu_riscv32`, and one month ago, it works for `test_compile_runtime` and `test_relay` in `test_zephyr.py`, here is my [code](https://github.com/Dream-math/Riscv-backend). But I find tvm code has cha

[Apache TVM Discuss] [Questions] [Tensorize] how to use tensorize for composition op(eg. conv+relu)

@aca88 Looks like i'm running into the same issue :frowning: Can you point to the code of VTA where they do this tensorization bypass? Thanks! --- [Visit Topic](https://discuss.tvm.apache.org/t/tensorize-how-to-use-tensorize-for-composition-op-eg-conv-relu/2336/10) to respond. You are

[Apache TVM Discuss] [Questions] TVM Support for FPGA

Hi @Amalik! For Xilinx FPGA's you might also want to look into VITIS-AI Codegen. https://tvm.apache.org/docs/deploy/vitis_ai.html (I have no experience with this myself though) best regards! --- [Visit Topic](https://discuss.tvm.apache.org/t/tvm-support-for-fpga/9551/3) to respond. You a