fix quantization
This commit is contained in:
@@ -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
|
||||||
|
|||||||
Reference in New Issue
Block a user