[Benchmark] Add benchmark scripts for block sparse attention #114
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This commit introduces two new example scripts demonstrating advanced GEMM (matrix multiplication) techniques: - `example_tilelang_gemm_splitk.py`: Implements a Split-K GEMM kernel using TileLang - `example_tilelang_gemm_streamk.py`: Implements a Stream-K GEMM kernel using TileLang Both examples showcase different parallel computation strategies for matrix multiplication, with comprehensive testing using PyTorch reference implementations.
Clean up and improve code formatting for the SplitK and StreamK GEMM example scripts: - Remove unused import (Profiler) in splitk example - Simplify line breaks and improve code readability - Standardize indentation and remove unnecessary whitespace - Optimize atomic add and copy operations for better clarity
This commit introduces comprehensive block sparse attention benchmarks for different libraries: - TileLang block sparse FMHA implementation - Triton block sparse FMHA implementation - PyTorch reference block sparse FMHA implementation - FlashAttention dense FMHA reference implementation The benchmarks include: - Configurable benchmark parameters (batch size, heads, sequence length, etc.) - Sparse mask generation using top-k and threshold methods - Performance measurement for different sparse attention configurations - Utility functions for mask generation and benchmarking
- Add Ruff linter ignore comments to benchmark files - Improve code formatting and line breaks - Remove unused imports - Standardize print statement formatting - Enhance code readability across multiple library benchmarks
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This pull request introduces several new benchmarking scripts for block-sparse attention mechanisms using different libraries and configurations. These changes are aimed at improving the performance analysis of sparse attention models. The most important changes include the addition of new benchmarking scripts for dense, tilelang, torch, and triton implementations, as well as the inclusion of a new dependency in the requirements file.
New Benchmarking Scripts:
benchmark/blocksparse_attention/benchmark_library_dense_fmha.py: Added a new benchmarking script for dense FlashAttention using theflash_attnlibrary.benchmark/blocksparse_attention/benchmark_tilelang_block_sparse_fmha.py: Added a new benchmarking script for block-sparse attention using thetilelanglibrary.benchmark/blocksparse_attention/benchmark_torch_block_sparse_fmha.py: Added a new benchmarking script for block-sparse attention using PyTorch.benchmark/blocksparse_attention/benchmark_triton_block_sparse_fmha.py: Added a new benchmarking script for block-sparse attention using thetritonlibrary.Configuration and Dependencies:
benchmark/blocksparse_attention/benchmark_configs.py: Added a configuration file with predefined benchmark settings.benchmark/blocksparse_attention/requirements.txt: Addedflash-attnas a new dependency.