Update llama-3.1-8b-instruct.mdx

fpagny · web-flow · commit dc98cd171518 · 2025-02-10T14:01:53.000+01:00
diff --git a/pages/managed-inference/reference-content/llama-3.1-8b-instruct.mdx b/pages/managed-inference/reference-content/llama-3.1-8b-instruct.mdx
@@ -34,9 +34,9 @@ meta/llama-3.1-8b-instruct:bf16
 | Instance type  | Max context length |
 | ------------- |-------------|
 | L4      | 96k (FP8), 27k (BF16) | 
-| L40S    | 96k (FP8), 27k (BF16) | 
-| H100      | 128k (FP8, BF16)
-| H100-2      | 128k (FP8, BF16)
+| L40S    | 128k (FP8, BF16) | 
+| H100      | 128k (FP8, BF16) |
+| H100-2      | 128k (FP8, BF16) |
 
 ## Model introduction
 
