Philipp van Kempen
Philipp van Kempen
It might be not really related to the Issue but I managed to get the Client Applet running using CheerpJ to compile from JAR to HTML5+JS. As mentioned before I...
> Due to the nature of the rewrite (absolutely everything network related :D) it will be a very big PR, @PhilippvK would you like me to create draft PR which...
CC @rafzi @panickal-xmos
> The upstream commit on which the patch is based is mentioned as [17b795d4233844144624df04c11ca1d967e81033](https://github.com/mnakhaei/amintflitemicro/commit/17b795d4233844144624df04c11ca1d967e81033) which seems to be a fork of tflite-micro. Has this been selected for some reason? Oh,...
Look like you are using an old c++ standard for compiling the tflm lib. please try to add `TARGET_COMPILE_FEATURES(${LIB_NAME} PUBLIC cxx_std_14)` here: https://github.com/cpetig/tflite_micro_compiler/blob/00c7f67abdb1e3335b90bfa39076f7c324141f0d/cmake/FindTFLite.cmake#L151
It seems like CMake pulls the latest version of flatbuffers which might be incompatible with the schema generated for TFLM. You you try to add this code instead (replacing the...
@tvm-bot rerun
@JoGei I guess we can have another look at this after a rebase and switch to the M2-ISA-R generated CoreDSL2 architectures (`RV32IMACFD` instead of `RISCV`)
While the `ETISSPlugin` changes might be problematic, the `run_helper.sh.in` improvements would be a nice addition IMO.
Looks good for me. @wysiwyng @JoGei what do you think?