GitLab

- Removed unnecessary configurations from the @tilelang.jit decorator in `example_grouped_gemm_fwd.py`, simplifying the kernel compilation process.
- Updated the `grouped_gemm` function to accept a tuple for batch sizes, enhancing compatibility with the kernel invocation.
- Added logic in `warp_specialized_rewriter.cc` to track buffer usage in `CallNode` expressions, improving the handling of TMA load operations.

This refactor aims to streamline the code and improve maintainability while ensuring better performance in grouped matrix multiplication operations.
Co-authored-by: LeiWang1999 <leiwang1999@outlook.com>

* [Example] Update kernel compilation in examples to use @tilelang.jit

- Refactored multiple examples to eliminate the use of `tilelang.compile` for kernel creation, directly invoking the functions instead.
- Added `@tilelang.jit` decorators with appropriate output indices to enhance performance and maintainability.
- Improved code clarity by simplifying the kernel invocation process across various examples, ensuring consistency in how kernels are defined and executed.

* format

* Update example_tilelang_sparse_gqa_decode_varlen_indice.py

* Update example_dequant_gemm_fine_grained.py

* Update example_gemm_autotune.py

---------
Co-authored-by: Lei Wang <34334180+LeiWang1999@users.noreply.github.com>

* Introduced `example_grouped_gemm_fwd.py` and `example_grouped_gemm_bwd.py` to demonstrate grouped matrix multiplication with forward and backward operations.
* Implemented functions for grouped GEMM, input construction, and validation against PyTorch's implementation.
* Added command-line argument parsing for flexible input configuration, including batch sizes and matrix dimensions.
* Included a test function to validate the functionality with various input scenarios.

* Introduced a new example script `example_grouped_gemm.py` demonstrating grouped matrix multiplication using TileLang and PyTorch.
* Implemented functions for performing grouped GEMM, constructing inputs, and validating results against PyTorch's implementation.
* Added command-line argument parsing for flexible input configuration, including batch sizes and matrix dimensions.
* Included a test function to validate the grouped GEMM functionality with various input scenarios.