inference working

packages/node/meshnet_node/dashboard.py

@@ -0,0 +1,220 @@
+"""Live node status dashboard — rich TUI with plain-text fallback."""
+
+from __future__ import annotations
+
+import os
+import sys
+import time
+from collections import deque
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    pass
+
+
+def is_interactive_tty() -> bool:
+    """Return True when stdout is a real terminal (not CI / redirected / WSL2 dumb)."""
+    if not sys.stdout.isatty():
+        return False
+    term = os.environ.get("TERM", "")
+    if term in ("dumb", ""):
+        return False
+    return True
+
+
+def _format_uptime(seconds: float) -> str:
+    s = int(seconds)
+    h, rem = divmod(s, 3600)
+    m, sec = divmod(rem, 60)
+    return f"{h:02d}:{m:02d}:{sec:02d}"
+
+
+def _gpu_stats() -> list[dict]:
+    """Return per-GPU utilization and VRAM stats, or empty list on CPU."""
+    try:
+        import torch  # type: ignore[import]
+
+        if not torch.cuda.is_available():
+            return []
+        stats = []
+        for i in range(torch.cuda.device_count()):
+            props = torch.cuda.get_device_properties(i)
+            used = torch.cuda.memory_allocated(i)
+            total = props.total_memory
+            # Utilization requires pynvml; skip gracefully if not available
+            util = _nvml_gpu_util(i)
+            stats.append(
+                {
+                    "index": i,
+                    "name": props.name,
+                    "used_gb": used / 1e9,
+                    "total_gb": total / 1e9,
+                    "util_pct": util,
+                }
+            )
+        return stats
+    except ImportError:
+        return []
+
+
+def _nvml_gpu_util(index: int) -> int | None:
+    """Return GPU utilization % via pynvml, or None if unavailable."""
+    try:
+        import pynvml  # type: ignore[import]
+
+        pynvml.nvmlInit()
+        handle = pynvml.nvmlDeviceGetHandleByIndex(index)
+        rates = pynvml.nvmlDeviceGetUtilizationRates(handle)
+        return rates.gpu
+    except Exception:
+        return None
+
+
+class _EMA:
+    """Exponential moving average for tokens/sec."""
+
+    def __init__(self, alpha: float = 0.1):
+        self._alpha = alpha
+        self._value: float | None = None
+
+    def update(self, sample: float) -> float:
+        if self._value is None:
+            self._value = sample
+        else:
+            self._value = self._alpha * sample + (1 - self._alpha) * self._value
+        return self._value
+
+    @property
+    def value(self) -> float:
+        return self._value or 0.0
+
+
+def _make_bar(pct: float, width: int = 10) -> str:
+    filled = round(pct / 100 * width)
+    return "█" * filled + "░" * (width - filled)
+
+
+def run_dashboard(node, config: dict, start_time: float) -> None:
+    """Start the live dashboard. Blocks until Ctrl-C. Returns cleanly."""
+    if not is_interactive_tty():
+        _run_plain_loop(node, config, start_time)
+        return
+
+    try:
+        from rich.live import Live  # type: ignore[import]
+
+        _run_rich_dashboard(node, config, start_time)
+    except ImportError:
+        _run_plain_loop(node, config, start_time)
+
+
+def _build_rich_renderable(
+    node, config: dict, start_time: float, tps_ema: _EMA, prev_req: list[int]
+):
+    from rich.table import Table  # type: ignore[import]
+    from rich.panel import Panel  # type: ignore[import]
+    from rich.columns import Columns  # type: ignore[import]
+    from rich.text import Text  # type: ignore[import]
+
+    uptime = time.monotonic() - start_time
+    req_count = getattr(node, "chat_completion_count", 0)
+
+    # Tokens/sec EMA (approximate: 20 tokens per request heuristic when no real counter)
+    delta_req = req_count - prev_req[0]
+    prev_req[0] = req_count
+    if delta_req > 0:
+        approx_tokens = delta_req * 20
+        tps_ema.update(approx_tokens / 2.0)  # 2s interval
+
+    gpu_stats = _gpu_stats()
+
+    model_name = config.get("model_name") or config.get("model_hf_repo", "unknown").split("/")[-1]
+    shard = ""
+    if config.get("shard_start") is not None:
+        shard = f"  shard {config['shard_start']}–{config['shard_end']}"
+
+    # Header line
+    header = Text(
+        f"meshnet-node  {model_name} [{config.get('quantization', 'bf16')}]{shard}"
+        f"  up {_format_uptime(uptime)}",
+        style="bold white",
+    )
+
+    # GPU table
+    gpu_table = Table(show_header=False, box=None, padding=(0, 1))
+    gpu_table.add_column("label", style="dim", no_wrap=True)
+    gpu_table.add_column("bar", no_wrap=True)
+    gpu_table.add_column("vram", no_wrap=True, style="cyan")
+
+    if gpu_stats:
+        for g in gpu_stats:
+            util = g["util_pct"]
+            util_str = f"{_make_bar(util)}  {util:3d}%" if util is not None else "            n/a"
+            vram_str = f"VRAM {g['used_gb']:.1f}/{g['total_gb']:.1f} GB"
+            gpu_table.add_row(f"GPU {g['index']}  {g['name'][:20]}", util_str, vram_str)
+    else:
+        gpu_table.add_row("CPU mode", "", "no GPU detected")
+
+    # Stats panel
+    tps = tps_ema.value
+    bar_len = min(8, max(0, int(tps / 10)))
+    tps_bar = "▁▂▃▄▅▆▇█"[:bar_len].ljust(8)
+
+    stats_lines = [
+        f"Tokens/sec   {tps_bar}  {tps:.1f} t/s (EMA)",
+        f"Requests     {req_count:,} served",
+        f"Peers        0 connected  (gossip: US-017)",
+        f"TAI earned   0.00 TAI  (payments: US-006)",
+        f"Uptime       {_format_uptime(uptime)}",
+        "",
+        "[q] quit   [c] compact view",
+    ]
+
+    from rich.console import Group  # type: ignore[import]
+
+    return Panel(
+        Group(header, gpu_table, Text("\n".join(stats_lines))),
+        title="[bold green]meshnet-node[/bold green]",
+        border_style="green",
+    )
+
+
+def _run_rich_dashboard(node, config: dict, start_time: float) -> None:
+    from rich.live import Live  # type: ignore[import]
+
+    tps_ema = _EMA()
+    prev_req = [0]
+
+    try:
+        with Live(
+            _build_rich_renderable(node, config, start_time, tps_ema, prev_req),
+            refresh_per_second=0.5,
+            screen=False,
+        ) as live:
+            while True:
+                time.sleep(2)
+                live.update(
+                    _build_rich_renderable(node, config, start_time, tps_ema, prev_req)
+                )
+    except KeyboardInterrupt:
+        pass
+
+
+def _run_plain_loop(node, config: dict, start_time: float) -> None:
+    model_name = config.get("model_name") or config.get("model_hf_repo", "unknown").split("/")[-1]
+    try:
+        while True:
+            uptime = time.monotonic() - start_time
+            req = getattr(node, "chat_completion_count", 0)
+            gpu_stats = _gpu_stats()
+            vram_str = ""
+            if gpu_stats:
+                g = gpu_stats[0]
+                vram_str = f"  VRAM{g['used_gb']:.1f}GB"
+            print(
+                f"[{model_name}  req{req}{vram_str}  up{_format_uptime(uptime)}]",
+                flush=True,
+            )
+            time.sleep(2)
+    except KeyboardInterrupt:
+        pass