fix: vllm gpu utilization 2

2025-11-27 00:57:14 +01:00
parent eaa8e0ebab
commit 4d7c811a46
2 changed files with 2 additions and 2 deletions
--- a/services/vllm/config_llama.yaml
+++ b/services/vllm/config_llama.yaml
@@ -2,5 +2,5 @@ model: meta-llama/Llama-3.1-8B-Instruct
 host: "0.0.0.0"
 port: 8001
 uvicorn-log-level: "info"
-gpu-memory-utilization: 0.75
+gpu-memory-utilization: 0.9
 max-model-len: 20480