| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | """Validate the registry reference kernel against runtime dispatch.""" |
| 4 | |
| 5 | import pytest |
| 6 | |
| 7 | from vllm.platforms import current_platform |
| 8 | |
| 9 | if not current_platform.is_cuda_alike(): |
| 10 | pytest.skip("NVIDIA dispatch tests require CUDA", allow_module_level=True) |
| 11 | |
| 12 | from vllm.v1.worker.block_table import ComputeSlotMappingKernel |
| 13 | |
| 14 | |
| 15 | @pytest.mark.parametrize( |
| 16 | ("kv_cache_block_size", "blocks_per_kv_block", "block_size", "block_size_rep"), |
| 17 | [ |
| 18 | (256, 1, 256, 16), |
| 19 | (256, 4, 64, 16), |
| 20 | (64, 1, 64, 16), |
| 21 | (8, 1, 8, 2), |
| 22 | (4, 1, 4, 2), |
| 23 | ], |
| 24 | ) |
| 25 | def test_compute_slot_mapping_warmup_matches_runtime_specializations( |
| 26 | kv_cache_block_size: int, |
| 27 | blocks_per_kv_block: int, |
| 28 | block_size: int, |
| 29 | block_size_rep: int, |
| 30 | ) -> None: |
| 31 | kernel = ComputeSlotMappingKernel() |
| 32 | kwargs = dict( |
| 33 | kv_cache_block_size=kv_cache_block_size, |
| 34 | blocks_per_kv_block=blocks_per_kv_block, |
| 35 | total_cp_world_size=1, |
| 36 | total_cp_rank=0, |
| 37 | cp_kv_cache_interleave_size=1, |
| 38 | block_table_stride=32768, |
| 39 | block_size=block_size, |
| 40 | ) |
| 41 | expected = kernel.CompileKey( |
| 42 | kv_cache_block_size=kv_cache_block_size, |
| 43 | blocks_per_kv_block=blocks_per_kv_block, |
| 44 | total_cp_world_size=1, |
| 45 | total_cp_rank=0, |
| 46 | cp_kv_cache_interleave_size=1, |
| 47 | block_table_stride=16, |
| 48 | block_size=block_size_rep, |
| 49 | ) |
| 50 | |
| 51 | assert kernel.dispatch(**kwargs) == expected |
| 52 | assert kernel.get_warmup_keys(**kwargs) == [expected] |