padreofthegame opened a new issue, #13668: URL: https://github.com/apache/tvm/issues/13668
### Documentation Title & Type While looking into documentation related to working with pre-quantized models I observed few maybe minor issues, related to doc appearance in the web browser, mentioned below: * [Deploy a Framework-prequantized Model with TVM ](https://tvm.apache.org/docs/how_to/deploy_models/deploy_prequantized.html) * Looks like there is an unnecessary highlighted block at the beginning of the document, * At the bottom of the doocument looks like the TODO comment for TFLite model is obsolete since it is solved on the next page. * It would also be good to have uniform title convention for different frontends as in [Compile Deep Learning Models](https://tvm.apache.org/docs/how_to/compile_models/index.html) part (for example, Deploy a Framework-prequantized Model with TVM - PyTorch, Deploy a Framework-prequantized Model with TVM - TFLite, etc...) * [Deploy a Framework-prequantized Model with TVM - Part 3 (TFLite)](https://tvm.apache.org/docs/how_to/deploy_models/deploy_prequantized_tflite.html) * Unnecessary highlighted block at the beginning of the document. * Maybe discard Part 3 in the title of the document and just put TFLite without brackets on its place. Also I get through all documentation pages, and found occurrence of similar highlighted box, mostly at the beginning of the document, in the following pages: * [Introduction](https://tvm.apache.org/docs/tutorial/introduction.html) * [Compiling and Optimizing a Model with TVMC](https://tvm.apache.org/docs/tutorial/tvmc_command_line_driver.html) * [Getting Starting using TVMC Python: a high-level API for TVM](https://tvm.apache.org/docs/tutorial/tvmc_python.html) * [Compiling and Optimizing a Model with the Python Interface (AutoTVM)](https://tvm.apache.org/docs/tutorial/autotvm_relay_x86.html) * [Working with Operators Using Tensor Expression](https://tvm.apache.org/docs/tutorial/tensor_expr_get_started.html) * [Quick Start Tutorial for Compiling Deep Learning Models](https://tvm.apache.org/docs/tutorial/relay_quick_start.html) * [Making your Hardware Accelerator TVM-ready with UMA](https://tvm.apache.org/docs/tutorial/uma.html) * [How to optimize GEMM on CPU](https://tvm.apache.org/docs/how_to/optimize_operators/opt_gemm.html) * [How to optimize convolution on GPU](https://tvm.apache.org/docs/how_to/optimize_operators/opt_conv_cuda.html) * [Running TVM on bare metal Arm(R) Cortex(R)-M55 CPU and Ethos(TM)-U55 NPU with CMSIS-NN](https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_ethosu.html) * [Bring Your Own Datatypes to TVM](https://tvm.apache.org/docs/how_to/extend_tvm/bring_your_own_datatypes.html) cc @areusch @driazati -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
