| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | |
| 4 | import pytest |
| 5 | import torch |
| 6 | |
| 7 | from vllm.platforms import current_platform |
| 8 | from vllm.v1.watermarking.prfs import PhiloxPRF |
| 9 | |
| 10 | |
| 11 | def test_philox_compatibility_vector(): |
| 12 | contexts = torch.tensor([[1, 2, 3, 4], [4, 5, 6, 7]]) |
| 13 | token_ids = torch.tensor([7, 8]) |
| 14 | expected_mantissas = [[1661833, 10571167], [9742331, 13375724]] |
| 15 | expected = ( |
| 16 | (torch.tensor(expected_mantissas, dtype=torch.float64) + 1) / (2**24 + 1) |
| 17 | ).to(torch.float32) |
| 18 | |
| 19 | assert torch.equal(PhiloxPRF(42).uniform(contexts, token_ids), expected) |
| 20 | |
| 21 | |
| 22 | def test_prf_pairs_contexts_with_target_tokens(): |
| 23 | contexts = torch.tensor([[1, 2, 3, 4], [4, 5, 6, 7]]) |
| 24 | token_ids = torch.tensor([[7], [8]]) |
| 25 | |
| 26 | assert PhiloxPRF(42).uniform(contexts, token_ids).shape == (2, 1) |
| 27 | |
| 28 | |
| 29 | @pytest.mark.skipif( |
| 30 | not current_platform.is_cuda_alike(), reason="requires a CUDA-like accelerator" |
| 31 | ) |
| 32 | @pytest.mark.parametrize("key", [42, 15726070495360670683]) |
| 33 | @pytest.mark.parametrize("context_width", [1, 4, 16]) |
| 34 | def test_philox_accelerator_matches_cpu(key: int, context_width: int): |
| 35 | contexts = torch.arange(2 * context_width, dtype=torch.int64).reshape( |
| 36 | 2, context_width |
| 37 | ) |
| 38 | token_ids = torch.arange(1024, dtype=torch.int64) |
| 39 | prf = PhiloxPRF(key) |
| 40 | |
| 41 | expected = prf.uniform(contexts, token_ids) |
| 42 | actual = prf.uniform(contexts.cuda(), token_ids.cuda()).cpu() |
| 43 | |
| 44 | torch.testing.assert_close(actual, expected, rtol=0, atol=0) |