jainapurva a9b29caeae Add attention benchmarking numbers to pytorch operator microbenchmarks (#164155) ... This pull request introduces a standardized YAML-based configuration system for transformer attention benchmarks, making it easier to run and manage comprehensive performance tests. It adds example configs, and a wrapper script to convert YAML configs into CLI arguments for the benchmark runner. #### Next Steps: CI Enablement: This change would further lead to running the attention ops in CI for regression tracking. #### Developer flow: (Run locally) `python score_mod.py --config configs/config_test.yaml` #### Enabling CI run: https://github.com/pytorch/pytorch/pull/165915 Pull Request resolved: https://github.com/pytorch/pytorch/pull/164155 Approved by: https://github.com/jbschlosser		2025-10-28 23:46:04 +00:00
..
configs	Add attention benchmarking numbers to pytorch operator microbenchmarks (#164155)	2025-10-28 23:46:04 +00:00
attention_bias_benchmarks.py	[9/N] Apply ruff UP035 rule (#165515)	2025-10-17 00:09:51 +00:00
better_transformer_vs_mha_functional.py	Fix unused Python variables outside torch/ and test/ (#136359)	2024-12-11 17:10:23 +00:00
config_utils.py	Add attention benchmarking numbers to pytorch operator microbenchmarks (#164155)	2025-10-28 23:46:04 +00:00
score_mod.py	Add attention benchmarking numbers to pytorch operator microbenchmarks (#164155)	2025-10-28 23:46:04 +00:00
sdp.py	PEP585 update - benchmarks tools torchgen (#145101)	2025-01-18 05:05:07 +00:00
sdpa.py	[9/N] Apply ruff UP035 rule (#165515)	2025-10-17 00:09:51 +00:00