Fix native macOS tailnet launch and Metal GPU probe (#756)

* macOS/Apple Silicon: detect Metal backend, surface MLX models, brew tmux hint

- hardware.py: add _detect_macos() via sysctl/system_profiler; report
  backend=metal + unified_memory on Apple Silicon instead of cpu_arm
- fit.py: add Apple Silicon (M1-M5) unified-memory bandwidths + metal
  FALLBACK_K so throughput estimates use the real bandwidth formula
- setup.py: Mac-specific 'brew install tmux' hint

Verified on M5 Pro 48GB: backend=metal, 273GB/s matched, 6 MLX models now
visible (were hidden), cuda still hides MLX, no new test failures.

* Fix native macOS tailnet launch and Metal GPU probe

---------

Co-authored-by: Elijah (Hermes) <hermes@local>
This commit is contained in:
elijaheck
2026-06-01 19:41:04 -07:00
committed by GitHub
parent a327df6936
commit c303a29670
4 changed files with 76 additions and 8 deletions

View File

@@ -90,7 +90,14 @@ cd odysseus
./start-macos.sh
```
It launches at `http://127.0.0.1:7860`. To build a clickable app wrapper:
It launches at `http://127.0.0.1:7860`. To expose it to your phone over a trusted LAN/VPN such as Tailscale, bind all interfaces:
```bash
ODYSSEUS_HOST=0.0.0.0 ./start-macos.sh
# then open http://<tailscale-ip>:7860
```
Keep auth enabled when binding outside loopback, and do not expose this port directly to the public internet. To build a clickable app wrapper:
```bash
./build-macos-app.sh

View File

@@ -1466,6 +1466,46 @@ def setup_cookbook_routes() -> APIRouter:
if gpus:
return {"ok": True, "gpus": gpus, "backend": "cuda", "source": "nvidia-smi"}
# Local Apple Silicon / Metal fallback. macOS has no nvidia-smi and no
# Linux /sys/class/drm tree, but services.hwfit.hardware already knows
# how to size the shared unified-memory GPU budget. Keep this route in
# sync so Cookbook's GPU picker doesn't show "nvidia-smi not found" on
# native Mac launches.
if not host and sys.platform == "darwin":
try:
from services.hwfit.hardware import detect_system
info = detect_system(fresh=True)
backend = str(info.get("backend") or "").lower()
if backend in {"metal", "mps", "apple"} and info.get("gpu_count", 0) > 0:
total_mb = int(float(info.get("gpu_vram_gb") or info.get("total_ram_gb") or 0) * 1024)
free_mb = int(float(info.get("available_ram_gb") or 0) * 1024)
if total_mb and (free_mb <= 0 or free_mb > total_mb):
free_mb = total_mb
used_mb = max(0, total_mb - max(0, free_mb))
return {
"ok": True,
"gpus": [{
"index": 0,
"name": info.get("gpu_name") or info.get("cpu_name") or "Apple Silicon GPU",
"uuid": "apple-metal-0",
"free_mb": max(0, free_mb),
"total_mb": max(0, total_mb),
"used_mb": used_mb,
"util_pct": 0,
"busy": bool(total_mb and (free_mb / total_mb) < 0.5),
"processes": [],
"backend": "metal",
"source": "apple-metal",
"unified_memory": True,
}],
"backend": "metal",
"source": "apple-metal",
"fallback_from": "nvidia-smi",
"nvidia_error": nvidia_error,
}
except Exception as e:
logger.warning("Apple Metal GPU fallback failed: %s", e)
amd_gpus = await _probe_amd_sysfs(host, ssh_port)
if amd_gpus:
return {

View File

@@ -26,7 +26,8 @@ GPU_BANDWIDTH = {
"m1 ultra": 800, "m1 max": 400, "m1 pro": 200, "m1": 68,
"m2 ultra": 800, "m2 max": 400, "m2 pro": 200, "m2": 100,
"m3 ultra": 800, "m3 max": 300, "m3 pro": 150, "m3": 100,
"m4 max": 410, "m4 pro": 273, "m4": 120,
"m4 max": 546, "m4 pro": 273, "m4": 120,
"m5 max": 546, "m5 pro": 273, "m5": 150,
}
# Pre-sort keys by length descending for correct substring matching

View File

@@ -17,6 +17,11 @@ REPO_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
cd "$REPO_DIR"
PORT="${ODYSSEUS_PORT:-7860}" # 7860, not 7000 — macOS AirPlay Receiver holds 7000.
HOST="${ODYSSEUS_HOST:-127.0.0.1}" # Set ODYSSEUS_HOST=0.0.0.0 for LAN/Tailscale access.
PROBE_HOST="$HOST"
if [ "$PROBE_HOST" = "0.0.0.0" ] || [ "$PROBE_HOST" = "::" ]; then
PROBE_HOST="127.0.0.1"
fi
# Friendly message on any failure — re-running is safe (every step is idempotent).
trap 'echo; echo "✗ Setup failed above. It is safe to re-run ./start-macos.sh."; exit 1' ERR
@@ -24,8 +29,8 @@ trap 'echo; echo "✗ Setup failed above. It is safe to re-run ./start-macos.sh.
echo "▶ Odysseus quick start for macOS"
# Fail fast if the port is already taken (e.g. a previous run still running).
if (exec 3<>"/dev/tcp/127.0.0.1/$PORT") 2>/dev/null; then
echo "✗ Port $PORT is already in use. Stop what's using it, or pick another port:"
if (exec 3<>"/dev/tcp/$PROBE_HOST/$PORT") 2>/dev/null; then
echo "✗ Port $PORT is already in use on $PROBE_HOST. Stop what's using it, or pick another port:"
echo " ODYSSEUS_PORT=7900 ./start-macos.sh"
exit 1
fi
@@ -100,8 +105,20 @@ echo "▶ Installing Python packages (first run downloads a few — can take a f
echo "▶ Preparing Odysseus…"
ODYSSEUS_SKIP_RUN_HINT=1 ./venv/bin/python setup.py
# 5. Launch. Bind to loopback only (safe default).
URL="http://127.0.0.1:$PORT"
# 5. Launch. Bind to loopback by default; opt into LAN/Tailscale with
# ODYSSEUS_HOST=0.0.0.0.
URL_HOST="$HOST"
if [ "$URL_HOST" = "0.0.0.0" ] || [ "$URL_HOST" = "::" ]; then
URL_HOST="127.0.0.1"
fi
URL="http://$URL_HOST:$PORT"
TAILSCALE_URL=""
if [ "$HOST" = "0.0.0.0" ] && command -v tailscale >/dev/null 2>&1; then
TS_IP="$(tailscale ip -4 2>/dev/null | head -n 1 || true)"
if [ -n "$TS_IP" ]; then
TAILSCALE_URL="http://$TS_IP:$PORT"
fi
fi
# Open the browser automatically once the server is accepting connections — so
# the URL isn't lost in the startup logs that keep scrolling. Runs in the
@@ -111,7 +128,7 @@ POLLER_PID=""
if [ -z "$ODYSSEUS_NO_OPEN" ] && command -v open >/dev/null 2>&1; then
(
for _ in $(seq 1 90); do
if (exec 3<>"/dev/tcp/127.0.0.1/$PORT") 2>/dev/null; then
if (exec 3<>"/dev/tcp/$PROBE_HOST/$PORT") 2>/dev/null; then
printf '\n'
printf ' ┌────────────────────────────────────────────┐\n'
printf ' │ ✓ Odysseus is ready — opening your browser │\n'
@@ -134,6 +151,9 @@ trap '[ -n "$POLLER_PID" ] && kill "$POLLER_PID" 2>/dev/null' EXIT INT TERM
echo
echo "▶ Starting Odysseus — it will open in your browser at $URL"
if [ -n "$TAILSCALE_URL" ]; then
echo " Tailscale/LAN URL: $TAILSCALE_URL"
fi
echo " (this takes a few seconds; press Ctrl+C here to stop)"
echo
"$PY" -m uvicorn app:app --host 127.0.0.1 --port "$PORT"
"$PY" -m uvicorn app:app --host "$HOST" --port "$PORT"