unsloth/tests/_zoo_aggressive_cuda_spoof.py

# Auto-generated by .github/workflows/consolidated-tests-ci.yml.
# Aggressive CUDA spoof for the consolidated CPU-only CI job. Extends
# tests/conftest.py's import-time harness with deeper patches that unblock
# more patch_* and unsloth_zoo init paths on a GPU-less runner. Imported by
# every shim test file before any unsloth / unsloth_zoo / transformers import.
#
# Only no-op or value-returning patches; tensor allocators are NOT replaced.
# The one exception is dropping `pin_memory=True` (a CUDA-host fast-copy hint
# that is meaningless here), which downgrades a CUDA-required call to CPU-OK.

from __future__ import annotations

import sys
import types
from typing import Any


def apply() -> None:
    """Apply the spoof. Idempotent: calling again has no effect."""
    import torch

    if getattr(torch.cuda, "_unsloth_consolidated_spoof", False):
        return

    # Device probes (cheap, value-returning)
    torch.cuda.is_available = lambda: True
    torch.cuda.device_count = lambda: 1
    torch.cuda.current_device = lambda: 0
    torch.cuda.is_initialized = lambda: True
    torch.cuda.set_device = lambda *a, **k: None
    torch.cuda.synchronize = lambda *a, **k: None
    torch.cuda.empty_cache = lambda *a, **k: None
    torch.cuda.get_device_name = lambda *a, **k: "NVIDIA A100-SPOOFED"
    torch.cuda.get_device_capability = lambda *a, **k: (8, 0)
    torch.cuda.is_bf16_supported = lambda *a, **k: True
    torch.cuda._is_in_bad_fork = lambda *a, **k: False  # type: ignore[attr-defined]

    class _Props:
        name = "NVIDIA A100-SPOOFED"
        major = 8
        minor = 0
        total_memory = 80 * 1024**3
        multi_processor_count = 108
        is_integrated = False
        is_multi_gpu_board = False

    torch.cuda.get_device_properties = lambda *a, **k: _Props()  # type: ignore[assignment]

    # cudart() wrapper
    class _CudaRt:
        @staticmethod
        def cudaMemGetInfo(device: int = 0):
            return (0, 80 * 1024**3)

        @staticmethod
        def cudaGetDeviceCount(*_a, **_k):
            return 0  # unused on the spoof path

        @staticmethod
        def cudaSetDevice(*_a, **_k):
            return 0

    torch.cuda.cudart = lambda: _CudaRt()  # type: ignore[assignment]

    # memory module
    try:
        import torch.cuda.memory as _cuda_memory  # type: ignore

        _cuda_memory.mem_get_info = lambda *a, **k: (0, 80 * 1024**3)
        _cuda_memory.memory_stats = lambda *a, **k: {}
        _cuda_memory.memory_allocated = lambda *a, **k: 0
        _cuda_memory.max_memory_allocated = lambda *a, **k: 0
        _cuda_memory.memory_reserved = lambda *a, **k: 0
        _cuda_memory.max_memory_reserved = lambda *a, **k: 0
        _cuda_memory.reset_peak_memory_stats = lambda *a, **k: None
    except Exception:
        pass

    # nvtx no-op stub
    nvtx_stub = types.ModuleType("torch.cuda.nvtx")
    nvtx_stub.range_push = lambda *a, **k: None  # type: ignore[attr-defined]
    nvtx_stub.range_pop = lambda *a, **k: None  # type: ignore[attr-defined]
    nvtx_stub.mark = lambda *a, **k: None  # type: ignore[attr-defined]
    sys.modules.setdefault("torch.cuda.nvtx", nvtx_stub)
    torch.cuda.nvtx = nvtx_stub  # type: ignore[attr-defined]

    # random API
    # CRITICAL: torch.manual_seed() calls torch.cuda.manual_seed_all(), so
    # routing the cuda seed APIs back through torch.manual_seed would
    # infinite-recurse (RecursionError in CI). No-op them; CUDA-side seeding
    # is meaningless on a GPU-less runner.
    torch.cuda.manual_seed = lambda *a, **k: None  # type: ignore[assignment]
    torch.cuda.manual_seed_all = lambda *a, **k: None  # type: ignore[assignment]
    # rng_state APIs: return a CPU-shaped placeholder, accept anything for set;
    # do NOT route through torch.{get,set}_rng_state (those touch the CPU RNG).
    import torch as _t

    _empty_rng_state = _t.empty(0, dtype = _t.uint8)
    torch.cuda.get_rng_state = lambda *a, **k: _empty_rng_state.clone()  # type: ignore[assignment]
    torch.cuda.set_rng_state = lambda *a, **k: None  # type: ignore[assignment]
    torch.cuda.get_rng_state_all = lambda *a, **k: [_empty_rng_state.clone()]  # type: ignore[attr-defined]
    torch.cuda.set_rng_state_all = lambda *a, **k: None  # type: ignore[attr-defined]
    torch.cuda.initial_seed = lambda *a, **k: 0  # type: ignore[assignment]
    torch.cuda.seed = lambda *a, **k: None  # type: ignore[assignment]
    torch.cuda.seed_all = lambda *a, **k: None  # type: ignore[assignment]

    # Stream / Event no-op classes
    class _NoopStream:
        def __init__(self, *a, **k): ...
        def __enter__(self):
            return self

        def __exit__(self, *a):
            return False

        def synchronize(self, *a, **k): ...
        def wait_stream(self, *a, **k): ...
        def query(self):
            return True

    class _NoopEvent:
        def __init__(self, *a, **k): ...
        def record(self, *a, **k): ...
        def wait(self, *a, **k): ...
        def query(self):
            return True

        def synchronize(self, *a, **k): ...
        def elapsed_time(self, *a, **k):
            return 0.0

    torch.cuda.Stream = _NoopStream  # type: ignore[assignment]
    torch.cuda.Event = _NoopEvent  # type: ignore[assignment]
    torch.cuda.stream = lambda s: s if s is not None else _NoopStream()  # type: ignore[assignment]
    torch.cuda.current_stream = lambda *a, **k: _NoopStream()  # type: ignore[assignment]
    torch.cuda.default_stream = lambda *a, **k: _NoopStream()  # type: ignore[assignment]

    # pin_memory drop: torch.empty(..., pin_memory=True) and friends raise on
    # a CPU-only build; strip the kwarg since pin_memory has no meaning here.
    for _name in (
        "empty",
        "zeros",
        "ones",
        "empty_like",
        "zeros_like",
        "ones_like",
        "rand",
        "randn",
        "randint",
    ):
        _orig = getattr(torch, _name, None)
        if _orig is None:
            continue

        def _wrap(
            *args: Any,
            _orig = _orig,
            **kwargs: Any,
        ):
            kwargs.pop("pin_memory", None)
            return _orig(*args, **kwargs)

        setattr(torch, _name, _wrap)

    # Tensor.pin_memory() instance method: also a no-op (return self).
    if hasattr(torch.Tensor, "pin_memory"):
        torch.Tensor.pin_memory = lambda self, *a, **k: self  # type: ignore[assignment]
    if hasattr(torch.Tensor, "is_pinned"):
        torch.Tensor.is_pinned = lambda self, *a, **k: False  # type: ignore[assignment]

    # amp.GradScaler: use the real one if importable (newer torch handles CPU),
    # else stub.
    try:
        import torch.cuda.amp  # type: ignore
    except Exception:
        cuda_amp = types.ModuleType("torch.cuda.amp")

        class _StubScaler:
            def __init__(self, *a, **k): ...
            def scale(self, x):
                return x

            def step(self, opt):
                opt.step()

            def update(self, *a, **k): ...
            def unscale_(self, *a, **k): ...
            def get_scale(self):
                return 1.0

            def is_enabled(self):
                return False

            def state_dict(self):
                return {}

            def load_state_dict(self, *a, **k): ...

        cuda_amp.GradScaler = _StubScaler  # type: ignore[attr-defined]
        sys.modules.setdefault("torch.cuda.amp", cuda_amp)
        torch.cuda.amp = cuda_amp  # type: ignore[attr-defined]

    # Sentinel
    torch.cuda._unsloth_consolidated_spoof = True  # type: ignore[attr-defined]


if __name__ == "__main__":
    apply()
    print("CUDA spoof applied.")