valknar/runpod
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: correct vLLM service port to 8000

Browse Source 
- Updated qwen-2.5-7b port from 8001 to 8000 in models.yaml
- Matches actual vLLM server default port configuration
- Tested and verified: orchestrator successfully loaded model and generated response
This commit is contained in:
Sebastian Krüger
2025-11-21 16:28:54 +01:00
parent 9a637cc4fc
commit 57b706abe6
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
model-orchestrator/models.yaml
View File

@@ -7,7 +7,7 @@ models:
type: text type: text
framework: vllm framework: vllm
service_script: models/vllm/server.py service_script: models/vllm/server.py
port: 8001 port: 8000
vram_gb: 14 vram_gb: 14
startup_time_seconds: 120 startup_time_seconds: 120
endpoint: /v1/chat/completions endpoint: /v1/chat/completions