mllm_shap.benchmarks package

Submodules

mllm_shap.benchmarks.bench_api_perf module

Micro-benchmarks for API/performance hotspots.

mllm_shap.benchmarks.bench_api_perf.bench_linear_num_samples_update(iters: int, repeats: int) → None

Benchmark in-place sampling budget update path used by experiments runner.

mllm_shap.benchmarks.bench_api_perf.bench_mask_hash(iters: int, mask_len: int, repeats: int) → None

Benchmark current mask hash implementation.

mllm_shap.benchmarks.bench_api_perf.bench_response_generation(n_masks: int, mask_len: int, repeats: int, n_jobs: int, verbose: bool) → None

Benchmark masked response generation orchestration.

mllm_shap.benchmarks.bench_api_perf.main() → None

Module contents

Benchmark utilities for mllm_shap.