mirror of
https://github.com/tile-ai/tilelang.git
synced 2026-10-31 08:13:15 +08:00
1e92d11cd252e014c44a1c0dc94deaade14c7d2f
28
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
|
8ce2778221 |
[CI][Refactor] Merge test CI workflow files into one (#973)
* refactor: merge test CI workflow files into one * chore: set `UV_INDEX_STRATEGY=unsafe-best-match` * feat: add AST test with Python 3.8 * feat: implement manual caching mechanism for self-hosted runners * refactor: simplify cache logic for self-hosted runners * chore: clear uv cache on failure * chore: print format.sh output to logs * chore: improve uv caching * chore: disable parallel test * chore: use `PYTHONDEVMODE=1` in CI * feat: enable coredump generation * fix: fix perfbench condition * Revert "feat: enable coredump generation" This reverts commit |
||
|
Cunxiao Niandpre-commit-ci[bot]
|
2ada4eca13 |
[CI] Removes debug print statements from the example. (#1030)
* [CI] Removes debug print statements from the example. * add parse args * [Lint]: [pre-commit.ci] auto fixes [...] * format --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com> |
||
|
Lei Wang
|
9d382973a2 |
[CI] Refactor import paths in dequantization examples to use dequantize_utils (#914)
* Update requirements and refactor benchmark script for deepseek_nsa example - Updated the requirements.txt to specify a fixed commit for the flash-linear-attention repository. - Refactored import paths in benchmark_nsa_fwd.py for better organization. - Added a new function to generate configurations for autotuning. - Modified the tilelang_sparse_attention function to accept parameters for block size, number of stages, and threads, enhancing flexibility. - Changed allocation of shared memory for accumulators to optimize performance. * Refactor import paths in dequantization examples to use dequantize_utils - Updated import statements in multiple dequantization example scripts to replace references to the removed utils.py file with the new dequantize_utils module. - Ensured consistency across example scripts for better organization and maintainability. |
||
|
|
8554cb01ae |
[Enhancement] Add a MXFP4 grouped GEMM example for FusedMoE (#811)
* [Enhancement] Enhance dequantization examples and utilities - Added a new example for grouped matrix multiplication with experts in `example_dequant_groupgemm_bf16_mxfp4_hopper.py`. - Improved dequantization logic in existing examples by replacing nested loops with vectorized operations for better performance. - Updated `torch_convert_bit_twiddling` function in `utils.py` to utilize parallel processing, enhancing efficiency and clarity in the conversion process. Co-authored-by: Zhengju Tang <97930865+tzj-fxz@users.noreply.github.com> * fix typos in docstrings * remove redundant code * [Format] Unreproducible debug with T.print * [BugFix] Correct dtype in ref dequantize; larger data distribution * [Format] * [Refactor] Clean up and optimize example_dequant_groupgemm_bf16_mxfp4_hopper.py and utils.py - Removed unnecessary cache disabling and manual seed setting in the example. - Simplified nested loops into parallelized operations for better readability and performance. - Updated the assertion function in utils.py to print detailed error messages. - Adjusted tensor sizes in examples * [Refactor] Update import path in example_dequant_gemm_fine_grained.py - Changed the import statement for `_tir_packed_to_unsigned_convert` from `bitblas.quantization` to `tilelang.quantize` to reflect the new module structure. * lint * rename and add test * lint * [Feature] Enhance autotuning and configuration generation in example_dequant_groupedgemm_bf16_mxfp4_hopper.py - Added a new function `get_configs()` to generate hyperparameter configurations for tuning. - Updated the `matmul` function to utilize autotuning with the new configurations. - Improve kernel performance via vectorization and threadblock swizzle. - Enhanced the main function to support the new autotuning inputs and updated parameters for better performance. * lint * fix typo * fix typo and lint * make ci format check happy * fix ci --------- Co-authored-by: Zhengju Tang <97930865+tzj-fxz@users.noreply.github.com> Co-authored-by: tzj-fxz <tzjfxz@gmail.com> |
||
|
Cunxiao Ni
|
4bcb1593d4 |
[Example] add w4a8 gemm kernel (#815)
* [Bugfix] fix autotune bug * [Example] add w4a8 gemm kernel * fix lint: pinned the version of `ml_dtypes` The version of ml_dtypes should be pinned in the dependency specification. If the version of ml_dtypes is too low, it may result in errors such as fp4 not being defined. * Renames example for dequantization GEMM * format * add w4a8 example to ci * fix lint |
||
|
Yichen Yan
|
5e52952201 |
[Lint] Add ruff config to check for useless spaces (#807)
* update lint config * Remove spaces for blank line * update |
||
|
Zhengju Tang
|
ea5483016d |
[MXFP4] Add 1D TMA copy for Scale tensor in MXFP4 GEMM (#766)
* [TMA] Add 1D TMA copy for Scale tensor * [Lint] * [Test] Add test for kernel * [BugFix] |
||
|
|
1774a1aae7 |
[Feature] Add 1D TMA support (#761)
* [Feature] Add 1D TMA support - Check the contiguous conditions of 1D TMA copy - Add new interface and params order of `tma_load` and `tma_store` call - Add 1D `tma_store` interface in sm90 template - Add elementwise kernel for 1D TMA example * [Lint] * [BugFix] Add conditions for 1D TMA copy on non-swizzle shared tensors * [Lint] * [BugFix] 1D TMA load * [README] Update GDN README for clarity and add acknowledgements (#758) - Improved formatting and clarity of the GDN kernel implementation description. - Updated requirement section to list dependencies in a clearer format. - Added an acknowledgements section to credit the developers and the Xiaomi LLM-Core Team for their contributions. * cutlass v4.2.0 supporting cuda 13 (#760) * [Lint] * [Lint] * [MXFP4] Add test for bf16&mxfp4 gemm * [BugFix] * [Lint] --------- Co-authored-by: Yu Cheng <54519279+chengyupku@users.noreply.github.com> Co-authored-by: Johnny <johnnync13@gmail.com> |
||
|
Zhengju Tang
|
fd199a4a7c |
[MXFP4] Add bias to MXFP4 GEMM kernel (#753)
* [MXFP4] Add bias to gemm kernel * [Lint] * [Lint] Rename "bias" to "Bias" |
||
|
Zhengju TangandLeiWang1999
|
796b3bbeb3 |
[MXFP4] Fix bugs and optimize exponential operation (#750)
* [MXFP4] Fix bugs - Optimize exp2 with shift operation to boost performance - Fix bug of simple dequantization function call - Fix bug of scaling factor with bias * [Lint] --------- Co-authored-by: LeiWang1999 <leiwang1999@outlook.com> |
||
|
Lei Wang
|
5c11d245ae |
[Refactor] Merge bulk copy into copy and improve layout inference for bulk copy (#746)
* [Refactor] Merge bulk copy into copy and refactor layout inference for bulk copy * Deleted the `bulk_copy` operator implementation and its header file as it is no longer needed. * Introduced a new function `cuTensorMapType()` to return the data type for CUDA tensor mapping. * Updated related files to reflect these changes, ensuring that the codebase remains clean and maintainable. * lint fix * Fix typos in intrinsic names and remove unused print statement in block_sparse_attn_tilelang.py. Updated references from `ptx_ldmatirx` to `ptx_ldmatrix` across multiple files for consistency. * remove bulk copy * Refactor copy and atomic add operations to support TMA lower configuration - Updated `GetCopyInst` to accept a `disable_tma_lower` parameter, allowing for conditional usage of TMA in bulk load/store operations. - Modified `Lower` method in `Copy` to incorporate the new TMA configuration. - Refactored `AtomicAdd::Lower` to streamline layout inference and vectorization logic. - Removed unused `disable_tma_lower` field from `LowerArgs` structure for clarity. - Enhanced atomic add vectorization by replacing the buggy implementation with a more robust loop vectorization approach. * Enhance TMA bulk copy logic in `LowerBulkCopy` method - Added a condition to set `desc.swizzle` to `CU_TENSOR_MAP_SWIZZLE_NONE` when `shared_layout` matches `linear_layout`, improving clarity in layout handling. - Updated warning log to provide more detailed information about fallback scenarios, including source and destination buffer names and shapes, enhancing debugging capabilities. * lint fix * Remove fallback logging for non-swizzled global layout in `LowerBulkCopy` method to streamline the bulk copy logic. This change enhances code clarity by eliminating unnecessary warning messages related to inner box dimensions. * Enhance reshape kernel compilation in `run_reshape` and `run_reshape_smem_1d_2_2d` functions - Updated the `tl.compile` method to include `pass_configs` that disable TMA lower and warp specialization, addressing shared memory layout transformation limitations. - Added TODO comments to indicate the need for further improvements in shared memory handling. * Update `native_sparse_attention` function to include TMA configuration options - Added `pass_configs` to the JIT decorator to disable TMA lower and warp specialization, addressing potential issues with shared memory layout transformations. - Updated comments to clarify modifications in tensor shapes for inference, specifically setting `q` sequence length to 1. * Refactor JIT decorator formatting in `native_sparse_attention` function - Improved readability by reformatting the JIT decorator parameters for `native_sparse_attention`, ensuring consistent style across the codebase. - No functional changes were made; this update focuses on code clarity and maintainability. * Enhance thread management and logging in TileLang compilation - Added a method to check if printing is enabled during compilation, improving control over logging behavior. - Updated the JIT kernel class to utilize the new method for logging compilation status, ensuring consistent and clear output. - Added comments to clarify the purpose of changes and improve code readability. * Add warp specialization scope and refactor register management in TileLang - Introduced a new constant `kWarpSpecializationScope` in `builtin.h` for better attribute management. - Removed the `SetMaxNRegCollector` class and its related logic from `warp_specialized_rewriter.cc`, streamlining the warp specialization process. - Added functions `annotate_producer_reg_dealloc` and `annotate_consumer_reg_alloc` in `builtin.py` to facilitate register management. - Implemented `AnnotateWarpGroupRegAlloc` in `__init__.py` to inject register allocation calls into warp-specialized functions, enhancing the overall register handling in the compilation process. * Refactor test for InjectSetMaxNReg pass in TileLang - Improved readability by restructuring conditional checks and assertions in the test cases. - Enhanced clarity in the collection of `set_max_nreg` calls by simplifying the logic. - Ensured consistent formatting and spacing throughout the test functions for better maintainability. * Enhance bulk copy and store checks in `Copy` class - Updated scope validation for source and destination tensors in `CheckBulkLoad` and `CheckBulkStore` methods to include both `shared.dyn` and `shared` as valid options. - Modified `CheckLDSMCopy` and `CheckSTSMCopy` methods to accommodate the new scope validation, ensuring compatibility with shared memory configurations. - Improved logging in `LowerBulkCopy` to provide clearer warnings regarding unsupported swizzle layouts, including source and destination names for better debugging. * lint fix |
||
|
Lei Wang
|
cb37bfef8f |
[Refactor] Refactor barrier management (#744)
* Introduce Barrier * Enhance CUDA kernel with new barrier management and post-processing support - Added a new CUDA kernel implementation in `example_mla_decode.py` for improved performance with shared memory barriers. - Refactored barrier handling in `codegen_cuda.cc` and `codegen_hip.cc` to utilize a more flexible mbarrier structure. - Updated intrinsic definitions from `ptx_stmatirx` to `ptx_stmatrix` across multiple files for consistency. - Introduced additional print statements for debugging in the lowering phase of the TileLang engine. - Enhanced the overall structure and readability of the codebase. * Remove unused barrier handling code in CUDA and HIP code generators to streamline the implementation. This change enhances code clarity and reduces complexity in the barrier management logic. * Enhance barrier management in TileLang - Introduced a new intrinsic `allocate_barrier` for dynamic barrier allocation in the TileLang framework. - Updated CUDA code generation to support the new barrier structure, allowing for improved synchronization in shared memory. - Refactored existing barrier handling logic to accommodate the new intrinsic and streamline code. - Added print statements for debugging purposes in various examples and the lowering phase of the TileLang engine. - Removed deprecated memory scope handling code to enhance clarity and maintainability. * lint fix * lint fix * Remove `allocate_barrier` intrinsic and related code from TileLang to streamline barrier management. This includes updates to CUDA code generation and the removal of associated Python wrappers, enhancing code clarity and maintainability. * Refactor logging in JITKernel to improve kernel compilation tracking - Removed unused import of `torch.backends` in the example file. - Introduced logging for kernel compilation in `JITKernel`, replacing print statements with structured logging for better traceability and debugging. - Added an assertion to ensure the presence of the `global_symbol` attribute in the kernel function. * Refactor dequantization tests and update barrier function - Removed the test for `example_dequant_gemm_bf16_fp4_hopper_serial` to streamline the testing suite. - Updated the `mbarrier_cp_async_arrive` function to support both pointer and non-pointer types, enhancing flexibility in barrier management. * Update CI configuration to increase pytest parallelism from 4 to 8 threads for improved test execution speed. * Fix typos in rasterization parameters and update import path for cached module - Corrected the spelling of `enable_rasteration` to `enable_rasterization` in the matmul function and its usage. - Updated the import statement for the `cached` module to reflect the new path in the cache submodule. - Added `StridedTensor` import in the language module for enhanced tensor functionality. * Update ci.yml |
||
|
coderabbitai[bot]andtzj-fxz
|
e3a80b70a2 |
📝 Add docstrings to mxfp4 (#732)
* 📝 Add docstrings to `mxfp4` Docstrings generation was requested by @LeiWang1999. * https://github.com/tile-ai/tilelang/pull/725#issuecomment-3191656561 The following files were modified: * `examples/bitnet-1.58b/kernel_benchmark/tilelang_bitnet_158_int8xint2_prefill.py` * `examples/dequantize_gemm/example_dequant_gemm_bf16_fp4_hopper.py` * `examples/dequantize_gemm/example_dequant_gemm_bf16_mxfp4_hopper.py` * `examples/dequantize_gemm/utils.py` * `examples/gemm/example_gemm_autotune.py` * `tilelang/intrinsics/utils.py` * `tilelang/language/__init__.py` * `tilelang/language/utils.py` * `tilelang/quantize/mxfp.py` * `tilelang/quantize/quantization.py` * [Lint] More accurate docstring * [Lint] --------- Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Co-authored-by: tzj-fxz <tzjfxz@gmail.com> |
||
|
|
24603e4a81 |
[Feature] Low-bit twiddling dequantization and FP4 GEMM (#725)
* [Dequant] Add bit-twiddling dequantize cuda for fp4-->bf16 * [Dequant] Add extern call and serial dequantization * [Dequant] Parallel Dequant wait for fence debug. * [Scale] Add scale matrix to mxfp4 gemm * [Remove] Remove fence-buggy example and some generated source cuda code * [MXFP4] Update initial version of MXFP4 GEMM * [Scale] Add scale to latest mxfp4 gemm * [Lint] * [BugFix] Load Scale, disabe TMA to recover performance * [Lint] * [Lint] * [Scale] Use L2 to hold Scale and enable TMA will slightly boost performance * [Lint] * Update example_dequant_gemm_bf16_fp4_hopper_serial.py * Remove deprecated dequantization examples for BF16 and MXFP4 in the dequantize_gemm directory. * Refactor dequantization examples for improved readability and consistency. Adjusted formatting in matmul function and added spacing for clarity. Updated function signatures and comments for better understanding. * Refactor index_to_coordinates usage in bitnet example and update dequantization example configurations. Removed the custom index_to_coordinates function and replaced it with the built-in version. Adjusted block_K parameter in dequantization example for consistency. * lint fix * ci fix * Remove non-existent example * [BugFix] Add smem swizzle to recover performance of TMA * [BugFix] Enough reg for producer when threads=512 --------- Co-authored-by: Lei Wang <34334180+LeiWang1999@users.noreply.github.com> Co-authored-by: LeiWang1999 <leiwang1999@outlook.com> |
||
|
|
569b0127c5 |
Low-bit kernels fix and implementation (#704)
* [MXFP4] Dequantize FP4 kernel example, MX scale todo * [BugFix] Fix the bug of fp4&fp16 exponential bias * [MXFP4] Add group scale factor for BF16xMXFP4 gemm * [Lint] * [Test] Add test script for BF16xMXFP4 gemm * [Lint] * [BugFix] Fix the shape of scale tensor * Update example_dequant_gemm_fp4_hopper.py --------- Co-authored-by: LeiWang1999 <leiwang1999@outlook.com> Co-authored-by: Lei Wang <34334180+LeiWang1999@users.noreply.github.com> |
||
|
Cunxiao NiandLei Wang
|
3db18726c7 |
[Example] Update examples to use @tilelang.jit (#597)
* [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> |
||
|
Lei Wang
|
7171aff6dc |
[Autotune] Introduce cache mechanism for auto tuner (#527)
* [Enhancement] Add commit ID to versioning and improve logging initialization * Updated `get_tilelang_version` to include an optional commit ID in the version string. * Enhanced the `TileLangBuilPydCommand` to write the version with commit ID to the VERSION file during the build process. * Introduced a new function `get_git_commit_id` in `version.py` to retrieve the current git commit hash. * Refactored logger initialization in `autotuner/__init__.py` to ensure handlers are set up only once, improving performance and clarity. * Minor fixes in `flatten_buffer.cc` and `kernel_cache.py` for better handling of versioning and logging. * [Refactor] Enhance AutoTuner and JITKernel for improved performance and caching * Refactored the AutoTuner class to include new methods for setting compilation and profiling arguments, enhancing configurability. * Introduced caching mechanisms for tuning results, allowing for faster retrieval of previously computed configurations. * Updated JITKernel to store tuning results, including latency and configuration details, improving the kernel's performance tracking. * Added new methods for generating cache keys and saving/loading results to/from disk, streamlining the tuning process. * Enhanced the overall structure and readability of the autotuning logic, ensuring better maintainability and clarity. * Minor adjustments in related modules to support the new caching and profiling features. * [Refactor] Clean up code formatting and improve readability in AutoTuner and related modules * Consolidated import statements and removed unnecessary line breaks for better readability. * Standardized function argument formatting across the AutoTuner and CompileArgs classes. * Enhanced consistency in the use of whitespace and indentation throughout the codebase. * Minor adjustments in the Profiler and JITKernel classes to improve clarity and maintainability. * Ensured that all changes adhere to the project's coding style guidelines. * [Refactor] Remove redundant type hints in AutoTuner modules * Simplified import statements in `__init__.py` and `param.py` by removing unnecessary duplicate type hints for `Any`. * Improved code readability and maintainability by streamlining type imports across the AutoTuner module. * [Refactor] Update AutoTuner configuration for improved profiling and target detection * Enhanced the AutoTuner configuration across multiple examples by adding `set_profile_args` to better manage profiling settings. * Standardized the use of `target="auto"` in compile arguments to ensure automatic target detection. * Removed redundant target specifications in certain instances to streamline the configuration process. * Improved overall clarity and maintainability of the autotuning logic in various example scripts. * [Refactor] Simplify code formatting and improve readability in example scripts * Consolidated function argument formatting in `benchmark_mla_decode_amd_tilelang.py`, `example_elementwise_add.py`, and `performance.py` for better clarity. * Removed unnecessary line breaks and standardized argument placement across multiple files. * Enhanced overall code readability and maintainability in autotuning examples and performance scripts. * [Refactor] Update JIT decorator usage across multiple files * Removed redundant parameters from the JIT decorator in various benchmark and example scripts, simplifying the code. * Standardized the import of the JIT decorator from `tilelang`, enhancing consistency across the codebase. * Improved overall readability and maintainability by consolidating import statements and cleaning up function definitions. * [Refactor] Standardize JIT decorator formatting across benchmark and example scripts * Simplified the formatting of the JIT decorator in multiple files by removing unnecessary line breaks. * Enhanced code readability and consistency in the usage of the JIT decorator across benchmark and example scripts. * Improved overall maintainability by ensuring uniformity in function definitions and decorator usage. |
||
|
Lei Wang
|
cde1886f2b |
[Refactor] Introduce quantize components of TileLang and add testing for dequant gemm exmaple (#494)
* Remove deprecated example_dequant_gemm.py and add DataType import in __init__.py * lint fix * lint fix * Refactor dequantization examples to use tilelang imports and update data type handling in quantization utilities * lint fix |
||
|
Lei Wang
|
66c7f6a13e |
[Bugfix] Updated autotune usage in the examples to align with the latest changes (#309)
* [Enhancement] Add support for CUDA architecture 8.9 in GEMM template - Introduced conditional inclusion of "gemm_sm89.h" for CUDA architectures 8.9 and above, enhancing compatibility with newer hardware. - This change ensures that the GEMM template can leverage optimizations specific to the 8.9 architecture, improving performance for users with compatible GPUs. * lintfix * [Refactor] Clean up includes in gemm_sm89.h - Removed duplicate inclusion of "common.h" and added "cuda_fp8.h" for improved clarity and organization. - This change enhances the maintainability of the code by ensuring that header files are included only once and in a logical order. * [Enhancement] Improve KernelCache with in-memory caching and detailed docstrings - Added an in-memory cache to the KernelCache class to enhance performance by reducing disk access. - Updated the __new__ method to initialize the memory cache and added logic to check the cache before loading from disk. - Enhanced docstrings across multiple methods to provide clearer explanations of parameters and return values, improving code readability and maintainability. - Implemented a clear_cache method to clear both in-memory and disk caches, ensuring efficient cache management. * lint fix * typofix * [Refactor] Update matmul and flashattn function calls to return structured results - Modified the matmul and flashattn function calls to return a single object containing latency, configuration, and reference latency, improving code clarity and reducing the number of returned variables. - Updated all relevant instances in benchmark and example scripts to accommodate the new return structure, ensuring consistent usage across the codebase. * lint fix |
||
|
Lei Wang
|
bf8a6fc142 |
[Refactor] Deprecated T.Buffer as arguments and rename related calls into T.Tensor (#281)
* [Refactor] Improve flash attention example and layout comparison logic - Removed unnecessary annotation for `lse_local_split` in the flash attention example to streamline the code. - Updated the handling of `lse_local_split` to utilize parallel processing for better performance. - Refactored kernel compilation and profiling logic to enhance clarity and maintainability in the flash attention example. - Added a condition in `FragmentNode::IsEqual` to handle broadcast cases, improving the robustness of layout comparisons. * lint fix * [Enhancement] Add support for shared memory scope in Fill operation - Introduced handling for `shared.dyn` and `shared` memory scopes in the Fill operation. - Implemented parallel operation and layout inference for improved performance in shared memory scenarios. - Updated thread loop partitioning and vectorization logic to accommodate new memory scope handling. * [Refactor] Remove deprecated decorator and enhance Cython kernel handling - Removed the deprecated decorator from the main module and added a new implementation in the utils module for better organization. - Introduced a pointer map in the Cython kernel adapter to manage pointer arguments, improving runtime shape resolution. - Updated the Cython kernel wrapper to utilize the new pointer map for handling kernel arguments. - Enhanced error checking in the tensor utility functions to ensure static shapes are enforced. - Added a new proxy module for buffer and tensor handling, streamlining the interface for TIR programs. * [Feature] Add matrix multiplication test and kernel implementation - Introduced a new test file `test_tilelang_language_ptr.py` that implements a matrix multiplication function using TileLang's primitives. - The `matmul_test` function defines a kernel for performing tile-level GEMM operations with customizable block sizes and data types. - Added a `run_matmul` function to compile and execute the kernel, along with a test function to validate the implementation. - Updated the `proxy.py` file to enhance type handling for buffer and tensor proxies, ensuring compatibility with TIR programs. - Minor formatting improvements in `deprecated.py` for better readability. * lint fix * [Refactor] Update tensor creation in matrix multiplication test - Replaced `T.Tensor.from_ptr` with `T.make_tensor` in `matmul_test` for improved clarity and consistency. - Updated imports in `__init__.py` to include `make_tensor`. - Added `make_tensor` function in `proxy.py` to streamline tensor creation from pointers. * [Refactor] Update tensor definitions across multiple files - Replaced instances of `T.Tensor` with updated tensor definitions in various benchmark and example files to enhance consistency and clarity. - Adjusted tensor shapes and types in functions related to matrix multiplication, attention mechanisms, and other operations. - Improved documentation in README and example files to reflect changes in tensor usage. * lint fix * [Refactor] Update tensor types in attention and matrix multiplication examples - Replaced instances of `T.Tensor` with `T.SharedTensor` and `T.FragmentTensor` in various attention and matrix multiplication functions to improve consistency and clarity. - Adjusted tensor definitions in benchmark and example files to align with the new tensor types. - Enhanced the overall structure and readability of the code by standardizing tensor usage across multiple files. * lint fix * [Refactor] Update tensor types in GEMM example and test files - Replaced instances of `T.Tensor` with `T.LocalTensor` and `T.Buffer` in the GEMM example and related test functions to improve consistency and clarity. - Enhanced the overall structure of the code by standardizing tensor usage across multiple files, aligning with recent updates in tensor definitions. * [Refactor] Update tensor usage in customize.py - Replaced instances of `T.Tensor` with `T.Buffer` in the `reshape` and `view` functions to enhance consistency with recent tensor definitions. - Improved code clarity by standardizing buffer usage across the file. * [Refactor] Update tensor types in test_tilelang_transform_annotate_device_regions.py - Replaced instances of `T.Tensor` with `T.Buffer` in the `before` and `expected` methods of the `TestAnnotateThreadExtent` and `TestAnnotateDeviceScope` classes to enhance consistency with recent tensor definitions. - Improved code clarity by standardizing buffer usage across the test file. * [Refactor] Update tensor types to SharedBuffer and FragmentBuffer - Replaced instances of `T.SharedTensor` and `T.FragmentTensor` with `T.SharedBuffer` and `T.FragmentBuffer` across multiple benchmark, example, and test files to enhance consistency with recent tensor definitions. - Improved code clarity and structure by standardizing buffer usage in attention and matrix multiplication functions. * [Refactor] Introduce Tensor alias for Buffer in proxy.py - Added a new alias `Tensor` for `Buffer` in `proxy.py` to facilitate JIT compilation, ensuring that inputs and outputs are mapped with `torch.Tensor`. - This change enhances clarity and consistency in tensor usage across the codebase. |
||
|
Chaofan LinandLeiWang1999
|
0430cfe7fb |
[Bugfix] Fix Benchmark/Example Code for Autotuning (#254)
* fix tune args * lint * Refactor gemm example and autotuner logging - Updated `ref_program` in `example_gemm.py` to return the result of matrix multiplication instead of modifying an input parameter. - Changed logging filename in `__init__.py` from 'out.log' to 'autotuner.log' for better clarity. - Modified JIT kernel compilation process to include `out_idx` directly in the adapter creation, enhancing flexibility. - Improved validation of `result_idx` in `BaseKernelAdapter` to ensure it falls within valid bounds. * Refactor `ref_program` in `benchmark_matmul_intrinsic.py` to use the `@` operator for matrix multiplication instead of `torch.matmul`, simplifying the implementation by removing the unused parameter `C`. --------- Co-authored-by: LeiWang1999 <leiwang1999@outlook.com> |
||
|
Lei Wang
|
f2e99180d5 |
[Refactor] Phaseout LLVM Dependency by Making it Optional (#247)
* remove llvm build * [Refactor] Update kernel compilation and profiling in examples - Replaced `tilelang.lower` with `tilelang.compile` in multiple example scripts to streamline kernel compilation. - Updated profiling calls to utilize the new `get_profiler` method, enhancing performance measurement consistency. - Adjusted assertions and benchmarking methods to align with the new profiling structure across various examples, ensuring correctness and clarity in performance evaluations. * lint fix * License Update * [Refactor] Improve code formatting and documentation in CUDA header and HIP runtime files - Adjusted formatting in `cuda.h` for better readability, including alignment of comments and struct fields. - Cleaned up whitespace and improved comment clarity in `rt_mod_hip.cc` to enhance code maintainability. * [Refactor] Enhance formatting and clarity in CUDA header and HIP runtime files - Improved comment alignment and readability in `cuda.h`. - Cleaned up whitespace and formatting in `rt_mod_hip.cc` to enhance maintainability. * lint fix * lint fix * lint fix * lint fix * fix * License update * [Enhancement] Update JITKernel to use artifact for kernel source - Assigned the generated artifact to `self.artifact` for better management. - Updated kernel source references to use `artifact.kernel_source` for consistency in execution backend handling. * lint fix * Add @tilelang.testing.requires_llvm decorator to vectorization tests * Enhance setup.py and env.py for library management - Added functionality to remove original files after copying in CMakeBuild. - Updated TVM_LIBRARY_PATH in env.py to include the PyPI build library path for better integration. * Refactor TVM_LIBRARY_PATH assignment for improved readability in env.py * Refactor CMakeBuild file handling in setup.py - Added a check to ensure the target library directory exists before copying .so files. - Improved the logic for creating the target directory and copying files to enhance robustness. * bugfix * Rename BuildTLDebug to BuildTileLangCUDAWithoutCompile and update registration. Add @tilelang.testing.requires_llvm decorator to multiple tests for LLVM requirement. * lint fix * Enhance TileLang code generation by adding support for device code generation without compilation. Updated `host_codegen` and `device_codegen` functions to include new transformations and registration for `tilelang_hip_without_compile`. Refactored JIT kernel adapters to accommodate host and device modules, improving overall integration and flexibility. * lint fix * Add support for C target in device code generation - Updated `device_codegen_without_compile` to include handling for the C target by registering the `tilelang_cpp` function. * [Enhancement] Implement auto-clear cache feature based on environment variable * Added TILELANG_CLEAR_CACHE environment variable to control cache clearing. * Updated CI workflow to set TILELANG_CLEAR_CACHE during testing. * Modified cache initialization to clear cache if TILELANG_CLEAR_CACHE is set to true. * [Refactor] Update kernel invocation and import paths in tests and cache * Changed kernel invocation in `test_tilelang_kernel_dequantize_gemm.py` to return the result. * Updated import statements in `test_tilelang_kernel_int4_gemm_mma.py` to use `bitblas` instead of `tilelang`. * Refactored paths for artifact and parameters in `kernel_cache.py` for better maintainability. * [Refactor] Clean up whitespace and improve code formatting in kernel_cache.py * Removed unnecessary blank lines and adjusted spacing for better readability in the KernelCache class. * Enhanced overall code formatting to align with project standards. * [Enhancement] Add bfloat16 test case and improve kernel caching logic * Introduced a new test case for bfloat16 matrix multiplication in `test_tilelang_kernel_gemm_mma_intrinsic.py`. * Updated `KernelCache` to handle multiple kernel source files and improve error handling during saving and loading. * Refactored `JITKernel` to support instantiation from a database, enhancing flexibility in kernel management. * Adjusted `CtypesKernelAdapter` and `CythonKernelAdapter` to utilize the new kernel loading mechanism from the database. * Improved code formatting and readability across several files. * lint fix * Update bfloat16 matrix multiplication test case to use larger dimensions for improved coverage |
||
|
Lei Wang
|
de1ba1e4b3 |
[Refactor] Replace T.thread_binding with T.get_thread_binding in examples and test cases (#163)
* [Refactor] Update BitBLAS Benchmark with TileLang Carver Imports and Roller Hints Generation - Replace BitBLAS imports with TileLang Carver imports in benchmark_matmul.py - Modify roller hints generation using new TileLang Carver template and utility functions - Update get_roller_hints_from_func to handle None cases and improve return logic - Adjust DefaultPolicy to handle different codegen dictionary formats * [Refactor] Update Thread Binding and Import Statements in TileLang Kernels - Replace T.thread_binding() with T.get_thread_binding() across multiple kernel test files - Update import statements for MMA layout and macro generator in dequantize GEMM and FP8 examples - Move map_torch_type utility function to tilelang.utils.tensor - Remove unnecessary imports and improve code organization |
||
|
Lei Wang
|
362b3520b0 |
[Refactor] Simplify interface via replacing argument thread binding of intrinsics with KernelFrame.Current (#34)
* installation script fix * readme typo fix * doc fix for dequantize gemm * [Doc] remove CODE_OF_CONDUCT.md and SECURITY.md; update references in CONTRIBUTING.md * [Doc] add unit tests for AnnotateDeviceRegions transform; remove SUPPORT.md * update license * [Enhancement] add tensor supply handling for unsigned integers; improve error message for execution backend assertion * [Refactor] improve code readability by reformatting function signatures and assertions * [Refactor] replace torch.manual_seed with tilelang.testing.set_random_seed for consistency in random seed handling * [Refactor] unify thread binding variable naming across kernel and example files * [Refactor] remove unused thread binding parameter from matrix multiplication functions * [Refactor] remove unused thread binding parameter from matrix multiplication functions * [Refactor] enable main testing function in tilelang kernel gemm test * bug fix |
||
|
Lei Wang
|
7959d78662 |
[CI] Comprehensive Test cases Implementation of Matmul Dequantize (#32)
* installation script fix * readme typo fix * doc fix for dequantize gemm * [Doc] remove CODE_OF_CONDUCT.md and SECURITY.md; update references in CONTRIBUTING.md * [Doc] add unit tests for AnnotateDeviceRegions transform; remove SUPPORT.md * update license * [Enhancement] add tensor supply handling for unsigned integers; improve error message for execution backend assertion * [Refactor] improve code readability by reformatting function signatures and assertions * [Refactor] replace torch.manual_seed with tilelang.testing.set_random_seed for consistency in random seed handling |
||
|
Lei Wang
|
7b777b38ff |
[Doc] Fix installation scripts and docs for dequantize gemm (#20)
* installation script fix * readme typo fix * doc fix for dequantize gemm |
||
|
Lei Wang
|
fa51185717 |
[Lint] Overall Typo and Linting Fixes (#13)
* README.md fixed * update test ci * Lint and Typo Fix * Clang Format Lint Fix |
||
|
|
57ab687cf7 |
[Initialization] Migration of Codebase from Dev Branch into Main (#10)
* Add format.sh script for code formatting and linting * docs update * center align the title * lint fix * add ignore * Add .gitignore for 3rdparty directory * Add requirements-dev.txt, requirements-test.txt, and requirements.txt * 3rdparty * Add gemm.h, CMakeLists.txt, _ffi_api.py, __init__.py, runtime.h, reduce.h, loop_partition.h, utils.h, and loop_vectorize.h * Refactor CMakeLists.txt and include statements - Update CMakeLists.txt to use a newer version of CMake and add project name - Remove unnecessary include directories Fix include paths in layout.cc, codegen.cc, codegen.h, rt_mod.cc, frontend_legalize.cc, inject_pipeline.cc, layout_inference.cc, loop_vectorize.cc, and lower_tile_op.cc - Update include paths to use relative paths instead of absolute paths * Update submodule for 3rdparty/tvm * update * load dll first * Refactor CMakeLists.txt and include statements * Refactor CMakeLists.txt and include statements * git keep update * Refactor CMakeLists.txt and include statements * Refactor CMakeLists.txt and include statements * refactor code structure * Update Readme * CMakeLists Customized * update readme * update README * update readme * update usage * with TVM_IMPORT_PYTHON_PATH to handle own tvm build python import * annotate lower transform global func with `transform` prefix * Migrate Simplify Pass from tilelang tvm branch * enhance system environment handling with __init__ and CMake * Initial commit * CODE_OF_CONDUCT.md committed * LICENSE committed * README.md committed * SECURITY.md committed * SUPPORT.md committed * CODE_OF_CONDUCT Commit * LICENSE Commit * SECURITY Commit * SUPPORT Commit * Modify Support * Update README.md * security ci update * remove examples * Update and implement clang-format * add composable kernel components * Migrate from latest update * submodule update * Test update * Update License * Spell check * lint fix * add clang-tidy to apply static analysis for c source * update tilelang examples * Update Install Docs * Refactor filetree * Enhance Install * conflict resloved * annotate_version * Initial Update * test fix * install * Implement setup.py * lint fix * Separate Init * Separate test * docker file commit * add logo * Update Readme and Examples * update readme * update logo * Implement AMD Installation * Add License * Update AMD MI300x Benchmark * update README * update mi300 benchmark scripts * update ignore * enhance build scirpt * update image * enhance setup.py to remove duplicated libraries * remove debug files * update readme * update image * update gemm examples * update flashattention README * readme update * add cmake into requirements * libinfo fix * auto update submodule * lint fix * Fix AMD Build and Test * Update check for transpose attribute for CDNA Arch * typo fix for amd * Implement Matmul Benchmark * Refactor Code * [TypoFix] Fix GEMM Example * [Docs] Init Linear Attention README * [TYPO] Typo fix * [Lint] Lint Fix * enhance example with intrinsics * [Enhancement] Improve Buffer Collection during IR Parser * [Dev] Introduce Current classmethod to get current frame * submodule update * fake test pass update * support thread_extent_api * code optimize * Add GEMM function implementation for matrix multiplication * Update logging format to reflect TileLang in logger messages * Refactor CMakeLists.txt for improved readability and set default build type to Release * Support Gemm SS Primitives Implementation * [README] Upload Tile Language Logo (#5) * update logo * Update README.md to enhance formatting and center the title --------- Co-authored-by: microsoft-github-operations[bot] <55726097+microsoft-github-operations[bot]@users.noreply.github.com> Co-authored-by: Microsoft Open Source <microsoftopensource@users.noreply.github.com> Co-authored-by: Yu Cheng <yu.cheng@pku.edu.cn> |