We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 686707d commit f5d3caaCopy full SHA for f5d3caa
samples/model_repository/vllm_model/1/model.json
@@ -1,5 +1,5 @@
1
{
2
"model":"facebook/opt-125m",
3
- "gpu_memory_utilization": 0.3,
+ "gpu_memory_utilization": 0.1,
4
"enforce_eager": true
5
}
0 commit comments