| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | from types import SimpleNamespace |
| 4 | |
| 5 | import pytest |
| 6 | import torch |
| 7 | import torch.nn as nn |
| 8 | from torch.testing._internal.two_tensor import TwoTensor |
| 9 | |
| 10 | from vllm.config import ParallelConfig |
| 11 | from vllm.model_executor import parameter |
| 12 | from vllm.model_executor.model_loader.weight_checksum import ( |
| 13 | compute_tensor_digests, |
| 14 | zero_weights, |
| 15 | ) |
| 16 | from vllm.v1.worker import gpu_worker |
| 17 | from vllm.v1.worker.gpu_worker import Worker |
| 18 | |
| 19 | pytestmark = pytest.mark.cpu_test |
| 20 | |
| 21 | |
| 22 | class _Model(nn.Module): |
| 23 | def __init__(self): |
| 24 | super().__init__() |
| 25 | self.linear = nn.Linear(2, 2) |
| 26 | nn.init.ones_(self.linear.weight) |
| 27 | nn.init.ones_(self.linear.bias) |
| 28 | # A strided view, which cannot be reinterpreted as bytes in place. |
| 29 | self.strided = nn.Parameter(torch.arange(1.0, 7.0)[::2]) |
| 30 | self.scalar = nn.Parameter(torch.tensor(2.0)) |
| 31 | # Loading never restores buffers, so reset must leave them alone. |
| 32 | self.register_buffer("k_scale", torch.tensor(2.0)) |
| 33 | |
| 34 | |
| 35 | def test_digests_cover_every_parameter(): |
| 36 | assert set(compute_tensor_digests(_Model())) == { |
| 37 | "linear.weight", |
| 38 | "linear.bias", |
| 39 | "strided", |
| 40 | "scalar", |
| 41 | } |
| 42 | |
| 43 | |
| 44 | def test_zero_weights_changes_every_parameter_and_no_buffer(): |
| 45 | model = _Model() |
| 46 | before = compute_tensor_digests(model) |
| 47 | zero_weights(model) |
| 48 | after = compute_tensor_digests(model) |
| 49 | assert all(before[name] != after[name] for name in before) |
| 50 | assert model.k_scale.item() == 2.0 |
| 51 | |
| 52 | |
| 53 | def test_shared_weight_partitions_are_hashed_and_reset(monkeypatch): |
| 54 | monkeypatch.setattr(parameter, "get_tensor_model_parallel_rank", lambda: 0) |
| 55 | monkeypatch.setattr(parameter, "get_tensor_model_parallel_world_size", lambda: 1) |
| 56 | model = nn.Module() |
| 57 | model.transform = parameter.SharedWeightParameter(weight_loader=None) |
| 58 | model.transform.add_partition(0, object(), 2, 2) |
| 59 | model.transform.partitions[0].data.fill_(3.0) |
| 60 | |
| 61 | before = compute_tensor_digests(model) |
| 62 | zero_weights(model) |
| 63 | assert set(before) == {"transform.0"} |
| 64 | assert compute_tensor_digests(model) != before |
| 65 | |
| 66 | |
| 67 | def test_tensor_subclass_inner_tensors_are_hashed_and_reset(): |
| 68 | model = nn.Module() |
| 69 | model.weight = nn.Parameter( |
| 70 | TwoTensor(torch.ones(2, 2), torch.full((2, 2), 2.0)), requires_grad=False |
| 71 | ) |
| 72 | |
| 73 | before = compute_tensor_digests(model) |
| 74 | zero_weights(model) |
| 75 | assert set(before) == {"weight.a", "weight.b"} |
| 76 | assert all( |
| 77 | before[name] != digest for name, digest in compute_tensor_digests(model).items() |
| 78 | ) |
| 79 | |
| 80 | |
| 81 | def test_dense_dp_replicas_get_distinct_key_prefixes(monkeypatch): |
| 82 | for name in ("get_tp_group", "get_pp_group", "get_pcp_group"): |
| 83 | monkeypatch.setattr(gpu_worker, name, lambda: SimpleNamespace(rank_in_group=0)) |
| 84 | prefixes = [] |
| 85 | for dp_rank in (0, 1): |
| 86 | worker = object.__new__(Worker) |
| 87 | worker.parallel_config = ParallelConfig( |
| 88 | data_parallel_size=2, data_parallel_rank=dp_rank |
| 89 | ) |
| 90 | # Dense DP resets data_parallel_rank to 0 in each engine. |
| 91 | worker.parallel_config.reconfigure_for_independent_dp_rank() |
| 92 | prefixes.append(worker._weight_checksum_prefix()) |
| 93 | assert prefixes == ["dp0:pp0:pcp0:tp0:", "dp1:pp0:pcp0:tp0:"] |