Update AMD inference endpoint and token to 165.245.137.80

README.md

@@ -26,8 +26,8 @@ tags:
 ### ⚡ Live Status (Hackathon Mode)
 - **Primary Inference**: AMD Instinct MI300X (192GB VRAM)
 - **Backend**: FastAPI + vLLM on ROCm
-- **Current Server**: `165.245.143.46` (vLLM via Token Auth)
 - **Status**: ✅ **ONLINE** (Live Inference Active)
+- **Current Server**: `165.245.137.80` (vLLM via Token Auth)
 
 > **AMD + lablab.ai Hackathon** — Track 2 (AMD Developer Cloud) · Track 1 (AI Agents) · Track 3 (Vision & Multimodal AI)
 

agents.py

@@ -19,13 +19,13 @@ import httpx  # async HTTP — lightweight, no extra deps beyond requirements
 # Or use the Jupyter proxy route: http://165.245.143.46/proxy/8000
 AMD_INFERENCE_URL = os.environ.get(
     "AMD_INFERENCE_URL",
-    "http://165.245.143.46:8000"
+    "http://165.245.137.80"
 ).rstrip("/")
 
 # Token for the AMD inference server (if required)
 AMD_INFERENCE_TOKEN = os.environ.get(
     "AMD_INFERENCE_TOKEN",
-    "5peRa6unb0DdXvzB3Pbck48IgNTDmxeJSUvE4NdnhvW70FcaX"
+    "DiPipPSZoxb96rcrP7X+B0N5mTTEzxU/ziesgI/Z2NPo9xPKM"
 )
 
 # The model name vLLM is serving (used in the chat/completions request).