load("@fbcode_macros//build_defs:python_unittest.bzl", "python_unittest")

oncall("executorch")

python_unittest(
    name = "test_simple_sdpa",
    srcs = [
        "test_simple_sdpa.py",
    ],
    deps = [
        "//caffe2:torch",
        "//executorch/examples/models/llama:export_library",
        "//executorch/examples/models/llama:llama_transformer",
    ],
)

python_unittest(
    name = "test_pre_quantization_transforms",
    srcs = [
        "test_pre_quantization_transforms.py",
    ],
    deps = [
        "//caffe2:torch",
        "//executorch/examples/models/llama:export_library",
        "//executorch/examples/models/llama:llama_transformer",
        "//pytorch/ao:torchao",
    ],
)

python_unittest(
    name = "test_static_attention",
    srcs = [
        "test_static_attention.py",
    ],
    deps = [
        "//caffe2:torch",
        "//executorch/examples/models/llama:llama_transformer",
        "//executorch/examples/models/llama:static_attention",
    ],
)

python_unittest(
    name = "test_ring_kv_cache",
    srcs = [
        "test_ring_kv_cache.py",
    ],
    deps = [
        "//caffe2:torch",
        "//executorch/examples/models/llama:llama_transformer",
    ],
)

python_unittest(
    name = "test_ring_attention",
    srcs = [
        "test_ring_attention.py",
    ],
    preload_deps = [
        "//executorch/extension/llm/custom_ops:custom_ops_aot_lib",
        "//executorch/kernels/quantized:aot_lib",
    ],
    deps = [
        "//caffe2:torch",
        "//executorch/examples/models/llama:export_library",
        "//executorch/examples/models/llama:llama_transformer",
        "//executorch/examples/models/llama:custom_kv_cache",
        "//executorch/examples/models/llama:sdpa",
    ],
)

python_unittest(
    name = "test_replace_kv_cache",
    srcs = [
        "test_replace_kv_cache.py",
    ],
    preload_deps = [
        "//executorch/extension/llm/custom_ops:custom_ops_aot_lib",
        "//executorch/kernels/quantized:aot_lib",
    ],
    deps = [
        "//caffe2:torch",
        "//executorch/examples/models/llama:export_library",
        "//executorch/examples/models/llama:llama_transformer",
        "//executorch/examples/models/llama:custom_kv_cache",
        "//executorch/examples/models/llama:sdpa",
    ],
)

python_unittest(
    name = "test_export_llama_lib",
    srcs = [
        "test_export_llama_lib.py",
    ],
    preload_deps = [
        "//executorch/extension/llm/custom_ops:custom_ops_aot_lib",
    ],
    deps = [
        "//caffe2:torch",
        "//executorch/examples/models/llama:export_library",
        "//executorch/examples/models/llama:llama_transformer",
        "//executorch/extension/pybindings:portable_lib",
    ],
)