diff --git a/model-orchestrator/models.yaml b/model-orchestrator/models.yaml index d3e6a4b..613f0d2 100644 --- a/model-orchestrator/models.yaml +++ b/model-orchestrator/models.yaml @@ -7,7 +7,7 @@ models: type: text framework: vllm service_script: models/vllm/server.py - port: 8001 + port: 8000 vram_gb: 14 startup_time_seconds: 120 endpoint: /v1/chat/completions