hyungi/gpu-services
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: health_check timeout 3→5초 — MLX cold start 대응

Browse Source 
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Hyungi Ahn
2026-04-06 12:08:28 +09:00
parent 2b4d182b24
commit 9f0c527442
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
nanoclaude/services/model_adapter.py
View File

@@ -100,9 +100,9 @@ class ModelAdapter:
return data["choices"][0]["message"]["content"] return data["choices"][0]["message"]["content"]
async def health_check(self) -> bool: async def health_check(self) -> bool:
"""GET /v1/models — 3초 timeout.""" """GET /v1/models — 5초 timeout."""
try: try:
async with httpx.AsyncClient(timeout=3.0) as client: async with httpx.AsyncClient(timeout=5.0) as client:
resp = await client.get(f"{self.base_url}/v1/models") resp = await client.get(f"{self.base_url}/v1/models")
return resp.status_code < 500 return resp.status_code < 500
except Exception: except Exception: