software-engineering/edge-gitops
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix memory util

Browse Source
This commit is contained in:
HaimKortovich
2026-05-08 09:42:50 -05:00
parent 2f922279ef
commit b70f8063a8
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
clusters/k3s-dgx/nim-service/qwen.yaml
View File

@@ -45,7 +45,7 @@ spec:
- --served-model-name - --served-model-name
- Qwen/Qwen3.6-27B-FP8 - Qwen/Qwen3.6-27B-FP8
- --gpu-memory-utilization - --gpu-memory-utilization
- "0.90" - "0.85"
- --max-model-len - --max-model-len
- "256000" - "256000"
- --language-model-only - --language-model-only