ZacharyZhang-NY
9cb46c18d3
The 500-line rule and the one-line-comment rule were enforced only from
memory, so they drifted. bench/filesize_check.py now checks the budget on
every tracked source file, and it passes.
Split, with behaviour proven unchanged by comparing each moved function body
against HEAD byte for byte (53 training bodies, 21 benchmark bodies, 0
differences):
db.py 503 -> 396 store_search.py 105
bench/run.py 609 -> 351 query_set.py 80, report.py 211
benchmarks.py 619 -> 424 benchmark_scoring.py 262
training.py 1630 -> 94 training_{common,encode,metrics,datasets,lora,retrieval}
TrainingService stays as a thin facade for the CLI; the facade's parameter
lists are pinned against the module functions by inspect, which is what
catches a leaked self.
Deleted the eight top-level functions no file called, after fixing the scan
that had reported 201 false positives by skipping the defining file. The
v1/v2/v3 sweep found nothing to delete and says so: every remaining version
tag is an on-disk format marker, a migration step, a fixture name, or a
third-party model name.
Collapsed 39 multi-line comment blocks (86 lines) to one line each, keeping
the measured facts and error strings that justify the code.
269 tests pass; ruff clean; mypy 24 errors in 9 files against a 24-in-6
baseline, net zero; pyright 4, the same four HEAD measures.
103 lines
4.5 KiB
Python
103 lines
4.5 KiB
Python
"""The launch layer must describe the machine it runs on, not the one it was written on."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import os
|
|
import stat
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from ely_eye import profiles
|
|
from ely_eye.config import Settings
|
|
from ely_eye.proofs.training_trace import cuda_bf16_training
|
|
from ely_eye.training_metrics import require_cuda_bf16
|
|
|
|
|
|
def _stub_nvidia_smi(tmp_path: Path, monkeypatch, output: str, exit_code: int = 0) -> None:
|
|
bin_dir = tmp_path / "bin"
|
|
bin_dir.mkdir()
|
|
stub = bin_dir / "nvidia-smi"
|
|
stub.write_text(f"#!/bin/sh\nprintf '%s\\n' '{output}'\nexit {exit_code}\n", encoding="utf-8")
|
|
stub.chmod(stub.stat().st_mode | stat.S_IEXEC)
|
|
monkeypatch.setenv("PATH", f"{bin_dir}{os.pathsep}{os.environ['PATH']}")
|
|
|
|
|
|
def test_a_gpu_that_is_not_the_written_down_card_still_counts(tmp_path: Path, monkeypatch) -> None:
|
|
_stub_nvidia_smi(tmp_path, monkeypatch, "GPU 0: NVIDIA GeForce RTX 5090 (UUID: GPU-1234)")
|
|
monkeypatch.setattr(profiles, "uses_wsl", lambda: False)
|
|
assert profiles.gpu_available(Settings(home=tmp_path / "home")) is True
|
|
|
|
|
|
def test_a_machine_the_driver_cannot_see_reports_no_gpu(tmp_path: Path, monkeypatch) -> None:
|
|
_stub_nvidia_smi(tmp_path, monkeypatch, "nvidia-smi: command not found", exit_code=127)
|
|
monkeypatch.setattr(profiles, "uses_wsl", lambda: False)
|
|
assert profiles.gpu_available(Settings(home=tmp_path / "home")) is False
|
|
|
|
|
|
def test_the_distro_name_comes_from_settings(monkeypatch) -> None:
|
|
monkeypatch.setattr(profiles, "uses_wsl", lambda: True)
|
|
command = profiles.host_shell("true", Settings(home=Path("/tmp"), wsl_distro="Ubuntu-24.04"))
|
|
assert command == ["wsl.exe", "-d", "Ubuntu-24.04", "bash", "-lc", "true"]
|
|
|
|
|
|
def test_inside_wsl_the_local_shell_runs(monkeypatch, tmp_path: Path) -> None:
|
|
monkeypatch.setenv("WSL_DISTRO_NAME", "Ubuntu")
|
|
monkeypatch.setattr(profiles.shutil, "which", lambda name: "/mnt/c/WINDOWS/system32/wsl.exe")
|
|
assert profiles.uses_wsl() is False
|
|
monkeypatch.delenv("WSL_DISTRO_NAME")
|
|
assert profiles.uses_wsl() is True
|
|
assert profiles.host_shell("true", Settings(home=tmp_path / "home", wsl_distro="Ubuntu"))[0] == "wsl.exe"
|
|
|
|
|
|
def test_a_linux_host_is_pointed_at_the_shell_twin(monkeypatch) -> None:
|
|
monkeypatch.setattr(profiles, "uses_wsl", lambda: False)
|
|
assert profiles.launch_script("scripts/launch-sglang-live.ps1") == "scripts/launch-sglang-live.sh"
|
|
monkeypatch.setattr(profiles, "uses_wsl", lambda: True)
|
|
assert profiles.launch_script("scripts/launch-sglang-live.ps1") == "scripts/launch-sglang-live.ps1"
|
|
|
|
|
|
def test_the_training_verdict_does_not_name_a_card() -> None:
|
|
newer = {"cuda_available": True, "bf16_supported": True, "device_name": "NVIDIA GeForce RTX 5090"}
|
|
assert cuda_bf16_training(newer) is True
|
|
older = {"cuda_available": True, "bf16_supported": True, "device_name": "NVIDIA GeForce RTX 4080"}
|
|
assert cuda_bf16_training(older) is True
|
|
without_bf16 = {"cuda_available": True, "bf16_supported": False, "device_name": "NVIDIA GeForce RTX 4090"}
|
|
assert cuda_bf16_training(without_bf16) is False
|
|
|
|
|
|
class _FakeCuda:
|
|
def __init__(self, available: bool, bf16: bool) -> None:
|
|
self._available = available
|
|
self._bf16 = bf16
|
|
|
|
def is_available(self) -> bool:
|
|
return self._available
|
|
|
|
def is_bf16_supported(self) -> bool:
|
|
return self._bf16
|
|
|
|
|
|
class _FakeTorch:
|
|
def __init__(self, available: bool, bf16: bool) -> None:
|
|
self.cuda = _FakeCuda(available, bf16)
|
|
|
|
|
|
def test_training_refuses_a_machine_without_cuda_by_capability_not_card() -> None:
|
|
with pytest.raises(RuntimeError) as refused:
|
|
require_cuda_bf16(_FakeTorch(available=False, bf16=False))
|
|
assert "4090" not in str(refused.value)
|
|
require_cuda_bf16(_FakeTorch(available=True, bf16=True))
|
|
|
|
|
|
def test_every_profile_ships_a_script_for_this_host(tmp_path: Path, monkeypatch) -> None:
|
|
root = Path(__file__).resolve().parents[2]
|
|
monkeypatch.setattr(profiles, "uses_wsl", lambda: False)
|
|
linux = profiles.runtime_profile_report(Settings(home=tmp_path / "home"), root)
|
|
assert [item.name for item in linux.validations if not item.script_exists] == []
|
|
assert all(item.script.endswith(".sh") for item in linux.profiles), linux.profiles
|
|
monkeypatch.setattr(profiles, "uses_wsl", lambda: True)
|
|
windows = profiles.runtime_profile_report(Settings(home=tmp_path / "home"), root)
|
|
assert [item.name for item in windows.validations if not item.script_exists] == []
|
|
assert all(item.script.endswith(".ps1") for item in windows.profiles), windows.profiles
|