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

use defaults

Browse Source
This commit is contained in:
HaimKortovich
2026-05-11 11:36:59 -05:00
parent db6efb188c
commit 2d2df4bb0a
1 changed files with 0 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
clusters/k3s-dgx/nim-service/qwen.yaml
View File

@@ -64,10 +64,6 @@ spec:
- --max-num-seqs - --max-num-seqs
- "254" # ↑ Allow more concurrent sequences - "254" # ↑ Allow more concurrent sequences
- --enable-prefix-caching - --enable-prefix-caching
- --dtype
- "float" # Explicit FP8 encoding
- --quantization
- "fp8" # Explicit quantization backend
authSecret: hf-api-secret authSecret: hf-api-secret
storage: storage:
sharedMemorySizeLimit: 64Gi sharedMemorySizeLimit: 64Gi