Grant
ae8efa1754
- image/ FastAPI app: /api/status, /api/swap, /api/swap/{id}/stream, /api/test-connection
- models.yaml: 5-model catalog (qwen3-vl, gemma4, qwen36, qwen3-235b-fp8, qwen25-72b)
- README, runbook, known-issues
- Dry-run swap verified against live Spark 1 (gemma4 currently loaded)
44 lines
1.7 KiB
Python
44 lines
1.7 KiB
Python
from __future__ import annotations
|
|
import httpx
|
|
from .config import Settings
|
|
|
|
|
|
_TIMEOUT = 3.0
|
|
|
|
|
|
async def check_vllm(settings: Settings) -> dict:
|
|
if not settings.spark1_host:
|
|
return {"ok": False, "error": "spark1 not configured"}
|
|
try:
|
|
async with httpx.AsyncClient(timeout=_TIMEOUT) as c:
|
|
r = await c.get(f"http://{settings.spark1_host}:{settings.vllm_port}/v1/models")
|
|
r.raise_for_status()
|
|
ids = [m["id"] for m in r.json().get("data", [])]
|
|
return {"ok": True, "current_model": ids[0] if ids else None, "all": ids}
|
|
except Exception as e:
|
|
return {"ok": False, "error": str(e)}
|
|
|
|
|
|
async def check_parakeet(settings: Settings) -> dict:
|
|
if not settings.spark2_host:
|
|
return {"ok": False, "error": "spark2 not configured"}
|
|
try:
|
|
async with httpx.AsyncClient(timeout=_TIMEOUT) as c:
|
|
r = await c.get(f"http://{settings.spark2_host}:{settings.parakeet_port}/health")
|
|
r.raise_for_status()
|
|
return {"ok": True, "detail": r.json()}
|
|
except Exception as e:
|
|
return {"ok": False, "error": str(e)}
|
|
|
|
|
|
async def check_magpie(settings: Settings) -> dict:
|
|
if not settings.spark2_host:
|
|
return {"ok": False, "error": "spark2 not configured"}
|
|
try:
|
|
async with httpx.AsyncClient(timeout=_TIMEOUT) as c:
|
|
r = await c.get(f"http://{settings.spark2_host}:{settings.magpie_port}/v1/health/ready")
|
|
r.raise_for_status()
|
|
return {"ok": True, "detail": r.json() if r.headers.get("content-type", "").startswith("application/json") else r.text}
|
|
except Exception as e:
|
|
return {"ok": False, "error": str(e)}
|