Function _has_rocm_gpu

studio/install_python_stack.py:728–815

Return True only if an actual AMD GPU is visible (not just ROCm tools installed). Always returns False when an NVIDIA GPU is present -- NVIDIA takes priority on mixed hosts and prevents every detection path below (rocminfo, amd-smi, KFD sysfs) from producing a false positive even if

()

def _has_rocm_gpu() -> bool:
    """Return True only if an actual AMD GPU is visible (not just ROCm tools installed).

    Always returns False when an NVIDIA GPU is present -- NVIDIA takes
    priority on mixed hosts and prevents every detection path below
    (rocminfo, amd-smi, KFD sysfs) from producing a false positive even
    if ROCm tools are installed alongside the NVIDIA driver.
    """
    if _has_usable_nvidia_gpu():
        return False
    for cmd, check_fn in (
        # rocminfo: look for a real gfx GPU id (3-4 chars, nonzero first digit).
        # gfx000 is the CPU agent; ROCm 6.1+ also emits generic ISA lines like
        # "gfx11-generic"/"gfx9-4-generic" with only 1-2 digits before the dash,
        # which must not be treated as a real GPU.
        (
            ["rocminfo"],
            lambda out: bool(re.search(r"gfx[1-9][0-9a-z]{2,3}", out.lower())),
        ),
        # amd-smi list: require "GPU: <number>" data rows, not just a header
        (
            ["amd-smi", "list"],
            lambda out: bool(re.search(r"(?im)^gpu\s*[:\[]\s*\d", out)),
        ),
    ):
        exe = shutil.which(cmd[0])
        if not exe:
            continue
        # Skip amd-smi on Windows w/o a HIP SDK (avoids the UAC/DiskPart prompt);
        # rely on rocminfo / the sysfs fallback there.
        if cmd[0] == "amd-smi" and not _amd_smi_allowed():
            continue
        try:
            result = subprocess.run(
                [exe, *cmd[1:]],
                stdout = subprocess.PIPE,
                stderr = subprocess.DEVNULL,
                text = True,
                timeout = 10,
                env = _amd_smi_env() if cmd[0] == "amd-smi" else None,
            )
        except Exception:
            continue
        if result.returncode == 0 and result.stdout.strip():
            if check_fn(result.stdout):
                return True
    # sysfs KFD topology fallback (Linux only) -- matches install.sh's
    # runtime-only detection. On minimal package-managed installs (no
    # rocminfo / no amd-smi tools), the kernel exposes AMD GPUs via
    # /sys/class/kfd so `studio update` can still detect and repair.
    #
    # Guard: reject any KFD node whose properties file reports a non-AMD
    # vendor. With the NVIDIA open kernel module (driver 560+), NVIDIA GPUs
    # can register KFD topology nodes with a non-zero gpu_id; those nodes
    # have vendor_id 4318 (0x10DE) rather than the AMD value 4098 (0x1002).
    # Without this check the fallback returns True on NVIDIA-only systems,
    # causing _ensure_rocm_torch to install ROCm wheels on NVIDIA hardware.
    if sys.platform != "win32":