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

fix quantization

Browse Source
This commit is contained in:
HaimKortovich
2026-05-11 11:36:17 -05:00
parent ce65c6435b
commit db6efb188c
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

@@ -67,7 +67,7 @@ spec:
- --dtype - --dtype
- "float" # Explicit FP8 encoding - "float" # Explicit FP8 encoding
- --quantization - --quantization
- "fbgemm-fp8" # Explicit quantization backend - "fp8" # Explicit quantization backend
authSecret: hf-api-secret authSecret: hf-api-secret
storage: storage:
sharedMemorySizeLimit: 64Gi sharedMemorySizeLimit: 64Gi