| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | |
| 4 | """vLLM Attention Benchmarking Suite.""" |
| 5 | |
| 6 | from .batch_spec import ( |
| 7 | BatchRequest, |
| 8 | format_batch_spec, |
| 9 | get_batch_stats, |
| 10 | parse_batch_spec, |
| 11 | reorder_for_flashinfer, |
| 12 | split_by_type, |
| 13 | ) |
| 14 | from .common import ( |
| 15 | BenchmarkConfig, |
| 16 | BenchmarkResult, |
| 17 | MockLayer, |
| 18 | ResultsFormatter, |
| 19 | get_attention_scale, |
| 20 | is_mla_backend, |
| 21 | setup_mla_dims, |
| 22 | ) |
| 23 | |
| 24 | __all__ = [ |
| 25 | # Batch specification |
| 26 | "BatchRequest", |
| 27 | "parse_batch_spec", |
| 28 | "format_batch_spec", |
| 29 | "reorder_for_flashinfer", |
| 30 | "split_by_type", |
| 31 | "get_batch_stats", |
| 32 | # Benchmarking infrastructure |
| 33 | "BenchmarkConfig", |
| 34 | "BenchmarkResult", |
| 35 | "ResultsFormatter", |
| 36 | # Mock objects |
| 37 | "MockLayer", |
| 38 | # Utilities |
| 39 | "setup_mla_dims", |
| 40 | "get_attention_scale", |
| 41 | "is_mla_backend", |
| 42 | ] |