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

remove option

Browse Source
This commit is contained in:
HaimKortovich
2026-05-11 11:35:29 -05:00
parent 08106b6693
commit ce65c6435b
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
clusters/k3s-dgx/nim-service/qwen.yaml
View File

@@ -68,7 +68,6 @@ spec:
- "float" # Explicit FP8 encoding - "float" # Explicit FP8 encoding
- --quantization - --quantization
- "fbgemm-fp8" # Explicit quantization backend - "fbgemm-fp8" # Explicit quantization backend
- --sv2-transformer-bindings # Skip SA checks (small speedup)
authSecret: hf-api-secret authSecret: hf-api-secret
storage: storage:
sharedMemorySizeLimit: 64Gi sharedMemorySizeLimit: 64Gi