voice-to-notes/python/voice_to_notes/hardware/detect.py

"""GPU/CPU detection and VRAM estimation."""

from __future__ import annotations

import ctypes
import os
import platform
import subprocess
import sys
from dataclasses import dataclass


@dataclass
class HardwareInfo:
    """Detected hardware capabilities."""

    has_cuda: bool = False
    cuda_device_name: str = ""
    vram_mb: int = 0
    ram_mb: int = 0
    cpu_cores: int = 0
    recommended_model: str = "base"
    recommended_device: str = "cpu"
    recommended_compute_type: str = "int8"


def _detect_ram_mb() -> int:
    """Detect total system RAM in MB (cross-platform).

    Tries platform-specific methods in order:
    1. Linux: read /proc/meminfo
    2. macOS: sysctl hw.memsize
    3. Windows: GlobalMemoryStatusEx via ctypes
    4. Fallback: os.sysconf (most Unix systems)

    Returns 0 if all methods fail.
    """
    # Linux: read /proc/meminfo
    if sys.platform == "linux":
        try:
            with open("/proc/meminfo") as f:
                for line in f:
                    if line.startswith("MemTotal:"):
                        # Value is in kB
                        return int(line.split()[1]) // 1024
        except (FileNotFoundError, ValueError, OSError):
            pass

    # macOS: sysctl hw.memsize (returns bytes)
    if sys.platform == "darwin":
        try:
            result = subprocess.run(
                ["sysctl", "-n", "hw.memsize"],
                capture_output=True,
                text=True,
                check=True,
            )
            return int(result.stdout.strip()) // (1024 * 1024)
        except (subprocess.SubprocessError, ValueError, OSError):
            pass

    # Windows: GlobalMemoryStatusEx via ctypes
    if sys.platform == "win32":
        try:

            class MEMORYSTATUSEX(ctypes.Structure):
                _fields_ = [
                    ("dwLength", ctypes.c_ulong),
                    ("dwMemoryLoad", ctypes.c_ulong),
                    ("ullTotalPhys", ctypes.c_ulonglong),
                    ("ullAvailPhys", ctypes.c_ulonglong),
                    ("ullTotalPageFile", ctypes.c_ulonglong),
                    ("ullAvailPageFile", ctypes.c_ulonglong),
                    ("ullTotalVirtual", ctypes.c_ulonglong),
                    ("ullAvailVirtual", ctypes.c_ulonglong),
                    ("ullAvailExtendedVirtual", ctypes.c_ulonglong),
                ]

            mem_status = MEMORYSTATUSEX()
            mem_status.dwLength = ctypes.sizeof(MEMORYSTATUSEX)
            if ctypes.windll.kernel32.GlobalMemoryStatusEx(ctypes.byref(mem_status)):
                return int(mem_status.ullTotalPhys) // (1024 * 1024)
        except (AttributeError, OSError):
            pass

    # Fallback: os.sysconf (works on most Unix systems)
    try:
        page_size = os.sysconf("SC_PAGE_SIZE")
        phys_pages = os.sysconf("SC_PHYS_PAGES")
        if page_size > 0 and phys_pages > 0:
            return (page_size * phys_pages) // (1024 * 1024)
    except (ValueError, OSError, AttributeError):
        pass

    return 0


def detect_hardware() -> HardwareInfo:
    """Detect available hardware and recommend model configuration."""
    info = HardwareInfo()

    # CPU info
    info.cpu_cores = os.cpu_count() or 1

    # RAM info (cross-platform)
    info.ram_mb = _detect_ram_mb()

    # CUDA detection — verify runtime libraries actually work, not just torch detection
    try:
        import torch

        if torch.cuda.is_available():
            # Test that CUDA runtime libraries are actually loadable
            try:
                torch.zeros(1, device="cuda")
                info.has_cuda = True
                info.cuda_device_name = torch.cuda.get_device_name(0)
                info.vram_mb = torch.cuda.get_device_properties(0).total_mem // (1024 * 1024)
            except Exception as e:
                print(
                    f"[sidecar] CUDA detected but runtime unavailable: {e}. Using CPU.",
                    file=sys.stderr,
                    flush=True,
                )
    except ImportError:
        print("[sidecar] torch not available, GPU detection skipped", file=sys.stderr, flush=True)

    # Model recommendation based on hardware
    if info.has_cuda and info.vram_mb >= 8000:
        info.recommended_model = "large-v3-turbo"
        info.recommended_device = "cuda"
        info.recommended_compute_type = "int8"
    elif info.has_cuda and info.vram_mb >= 4000:
        info.recommended_model = "medium"
        info.recommended_device = "cuda"
        info.recommended_compute_type = "int8"
    elif info.ram_mb >= 16000:
        info.recommended_model = "medium"
        info.recommended_device = "cpu"
        info.recommended_compute_type = "int8"
    elif info.ram_mb >= 8000:
        info.recommended_model = "small"
        info.recommended_device = "cpu"
        info.recommended_compute_type = "int8"
    else:
        info.recommended_model = "base"
        info.recommended_device = "cpu"
        info.recommended_compute_type = "int8"

    return info