|
| 1 | +# Copyright 2026 Arm Limited and/or its affiliates. |
| 2 | +# |
| 3 | +# This source code is licensed under the BSD-style license found in the |
| 4 | +# LICENSE file in the root directory of this source tree. |
| 5 | + |
| 6 | +from typing import Tuple |
| 7 | + |
| 8 | +import pytest |
| 9 | + |
| 10 | +import torch |
| 11 | +from executorch.backends.arm._passes.insert_int32_casts_after_int64_placeholders import ( |
| 12 | + InsertInt32CastsAfterInt64PlaceholdersPass, |
| 13 | +) |
| 14 | +from executorch.backends.arm.test import common |
| 15 | +from executorch.backends.arm.test.tester.test_pipeline import ( |
| 16 | + EthosU55PipelineINT, |
| 17 | + EthosU85PipelineINT, |
| 18 | + TosaPipelineFP, |
| 19 | + TosaPipelineINT, |
| 20 | + VgfPipeline, |
| 21 | +) |
| 22 | +from transformers import LlamaConfig |
| 23 | +from transformers.cache_utils import StaticCache |
| 24 | + |
| 25 | +input_t = Tuple[torch.Tensor, torch.Tensor, torch.Tensor] |
| 26 | + |
| 27 | + |
| 28 | +test_configs = { |
| 29 | + "multihead_attention": LlamaConfig(num_attention_heads=32), |
| 30 | + "grouped_query_attention": LlamaConfig( |
| 31 | + num_attention_heads=32, num_key_value_heads=4 |
| 32 | + ), |
| 33 | + "multi_query_attention": LlamaConfig(num_attention_heads=32, num_key_value_heads=1), |
| 34 | +} |
| 35 | + |
| 36 | + |
| 37 | +@torch.no_grad() |
| 38 | +class StaticCacheModule(torch.nn.Module): |
| 39 | + def __init__( |
| 40 | + self, |
| 41 | + config: LlamaConfig, |
| 42 | + max_cache_len: int = 10, |
| 43 | + dtype: torch.dtype = torch.float32, |
| 44 | + ) -> None: |
| 45 | + super().__init__() |
| 46 | + |
| 47 | + assert dtype is torch.float32 |
| 48 | + |
| 49 | + self.config = config |
| 50 | + self.dtype = dtype |
| 51 | + |
| 52 | + self.cache = StaticCache(config=self.config, max_cache_len=max_cache_len) |
| 53 | + |
| 54 | + hidden_size = self.config.hidden_size |
| 55 | + num_attention_heads = self.config.num_attention_heads |
| 56 | + assert hidden_size is not None and num_attention_heads is not None |
| 57 | + |
| 58 | + self.hidden_size = hidden_size |
| 59 | + self.num_attention_heads = num_attention_heads |
| 60 | + |
| 61 | + self.cache.early_initialization( |
| 62 | + 1, |
| 63 | + self.num_attention_heads, |
| 64 | + self.hidden_size // self.num_attention_heads, |
| 65 | + self.dtype, |
| 66 | + torch.device("cpu"), |
| 67 | + ) |
| 68 | + |
| 69 | + for i in range(len(self.cache.layers)): |
| 70 | + self.register_buffer(f"cache_layer_keys_{i}", self.cache.layers[i].keys) |
| 71 | + self.register_buffer(f"cache_layer_values_{i}", self.cache.layers[i].values) |
| 72 | + |
| 73 | + def forward( |
| 74 | + self, |
| 75 | + key_states: torch.Tensor, |
| 76 | + value_states: torch.Tensor, |
| 77 | + cache_position: torch.Tensor, |
| 78 | + ) -> Tuple[torch.Tensor, torch.Tensor]: |
| 79 | + key, value = self.cache.update( |
| 80 | + key_states, |
| 81 | + value_states, |
| 82 | + layer_idx=0, |
| 83 | + cache_kwargs={ |
| 84 | + "cache_position": cache_position, |
| 85 | + }, |
| 86 | + ) |
| 87 | + |
| 88 | + return key.clone(), value.clone() |
| 89 | + |
| 90 | + def get_inputs(self) -> input_t: |
| 91 | + key_states = torch.randn( |
| 92 | + ( |
| 93 | + 1, |
| 94 | + self.num_attention_heads, |
| 95 | + 1, |
| 96 | + self.hidden_size // self.num_attention_heads, |
| 97 | + ), |
| 98 | + dtype=torch.float32, |
| 99 | + ) |
| 100 | + value_states = torch.randn( |
| 101 | + ( |
| 102 | + 1, |
| 103 | + self.num_attention_heads, |
| 104 | + 1, |
| 105 | + self.hidden_size // self.num_attention_heads, |
| 106 | + ), |
| 107 | + dtype=torch.float32, |
| 108 | + ) |
| 109 | + cache_position = torch.tensor([1], dtype=torch.int64) |
| 110 | + |
| 111 | + return key_states, value_states, cache_position |
| 112 | + |
| 113 | + |
| 114 | +@common.parametrize("test_data", test_configs) |
| 115 | +def test_static_cache_tosa_FP(test_data): |
| 116 | + module = StaticCacheModule(test_data).eval() |
| 117 | + pipeline = TosaPipelineFP[input_t]( |
| 118 | + module, |
| 119 | + module.get_inputs(), |
| 120 | + aten_op=[], |
| 121 | + exir_op=[], |
| 122 | + transform_passes=[InsertInt32CastsAfterInt64PlaceholdersPass()], |
| 123 | + ) |
| 124 | + pipeline.run() |
| 125 | + |
| 126 | + |
| 127 | +@pytest.mark.xfail( |
| 128 | + reason="TODO(MLETORCH-1818): Quantization for StaticCache is not yet supported." |
| 129 | +) |
| 130 | +@common.parametrize("test_data", test_configs) |
| 131 | +def test_static_cache_tosa_INT(test_data): |
| 132 | + module = StaticCacheModule(test_data).eval() |
| 133 | + pipeline = TosaPipelineINT[input_t]( |
| 134 | + module, |
| 135 | + module.get_inputs(), |
| 136 | + aten_op=[], |
| 137 | + exir_op=[], |
| 138 | + ) |
| 139 | + pipeline.run() |
| 140 | + |
| 141 | + |
| 142 | +@common.XfailIfNoCorstone300 |
| 143 | +@pytest.mark.xfail( |
| 144 | + reason="Quantization for StaticCache is not yet supported. Scatter operator is also not supported on U55." |
| 145 | +) |
| 146 | +@common.parametrize("test_data", test_configs) |
| 147 | +def test_static_cache_u55_INT(test_data): |
| 148 | + module = StaticCacheModule(test_data).eval() |
| 149 | + pipeline = EthosU55PipelineINT[input_t]( |
| 150 | + module, |
| 151 | + module.get_inputs(), |
| 152 | + aten_ops=[], |
| 153 | + ) |
| 154 | + pipeline.run() |
| 155 | + |
| 156 | + |
| 157 | +@common.XfailIfNoCorstone320 |
| 158 | +@pytest.mark.xfail( |
| 159 | + reason="TODO(MLETORCH-1818): Quantization for StaticCache is not yet supported." |
| 160 | +) |
| 161 | +@common.parametrize("test_data", test_configs) |
| 162 | +def test_static_cache_u85_INT(test_data): |
| 163 | + module = StaticCacheModule(test_data).eval() |
| 164 | + pipeline = EthosU85PipelineINT[input_t](module, module.get_inputs(), aten_ops=[]) |
| 165 | + pipeline.run() |
| 166 | + |
| 167 | + |
| 168 | +@common.SkipIfNoModelConverter |
| 169 | +@common.parametrize("test_data", test_configs) |
| 170 | +def test_static_cache_vgf_no_quant(test_data): |
| 171 | + module = StaticCacheModule(test_data).eval() |
| 172 | + pipeline = VgfPipeline[input_t]( |
| 173 | + module, |
| 174 | + module.get_inputs(), |
| 175 | + aten_op=[], |
| 176 | + exir_op=[], |
| 177 | + transform_passes=[InsertInt32CastsAfterInt64PlaceholdersPass()], |
| 178 | + quantize=False, |
| 179 | + ) |
| 180 | + pipeline.run() |
| 181 | + |
| 182 | + |
| 183 | +@common.SkipIfNoModelConverter |
| 184 | +@pytest.mark.xfail( |
| 185 | + reason="TODO(MLETORCH-1818): Quantization for StaticCache is not yet supported." |
| 186 | +) |
| 187 | +@common.parametrize("test_data", test_configs) |
| 188 | +def test_static_cache_vgf_quant(test_data): |
| 189 | + module = StaticCacheModule(test_data).eval() |
| 190 | + pipeline = VgfPipeline[input_t]( |
| 191 | + module, |
| 192 | + module.get_inputs(), |
| 193 | + aten_op=[], |
| 194 | + exir_op=[], |
| 195 | + quantize=True, |
| 196 | + ) |
| 197 | + pipeline.run() |
0 commit comments