Add L40S to Managed Inference.mdx

Update pages mentioning L4 to add L40S as a deployment option

Author: fpagny

ai-data/managed-inference/reference-content/bge-multilingual-gemma2.mdx

@@ -19,6 +19,7 @@ dates:
 |-----------------|------------------------------------|
 | Provider        | [baai](https://huggingface.co/BAAI)  |
 | Compatible Instances | L4 (FP32)    |
+| Compatible Instances | L40S (FP32)    |
 | Context size | 4096 tokens    |
 
 ## Model name
@@ -32,6 +33,7 @@ baai/bge-multilingual-gemma2:fp32
 | Instance type  | Max context length |
 | ------------- |-------------|
 | L4      | 4096 (FP32) | 
+| L40S    | 4096 (FP32) | 
 
 ## Model introduction