Apply suggestion from @liu-cong

vMaroon · liu-cong · web-flow · commit 988d2a522901 · 2025-08-26T15:25:31.000+03:00
Co-authored-by: Cong Liu &lt;conliu@google.com&gt;
diff --git a/pkg/epp/scheduling/framework/plugins/multi/prefix/plugin.go b/pkg/epp/scheduling/framework/plugins/multi/prefix/plugin.go
@@ -269,7 +269,7 @@ func hashPrompt(ctx context.Context, request *types.LLMRequest, cacheBlockSize i
 		loggerDebug.Info("Truncating input", "size", len(userInput), "max prefix blocks", maxPrefixBlocks, "block size", cacheBlockSize)
 		userInput = userInput[:maxPrefixBlocks*cacheBlockSize]
 	}
-	// Split the body into blocks of size cacheBlockSize. The +1 is to account for the model.
+	// Split the body into blocks of size cacheBlockSize. 
 	// If the last block is smaller than cacheBlockSize, it will be ignored.
 	res := make([]BlockHash, 0, 1+len(userInput)/cacheBlockSize)
 	// Add the model to the first block hash so that different models have different hashes even with the same body.

Original file line number	Diff line number	Diff line change
`@@ -269,7 +269,7 @@ func hashPrompt(ctx context.Context, request *types.LLMRequest, cacheBlockSize i`
`269`	`269`	`loggerDebug.Info("Truncating input", "size", len(userInput), "max prefix blocks", maxPrefixBlocks, "block size", cacheBlockSize)`
`270`	`270`	`userInput = userInput[:maxPrefixBlocks*cacheBlockSize]`
`271`	`271`	`}`
`272`		`- // Split the body into blocks of size cacheBlockSize. The +1 is to account for the model.`
	`272`	`+ // Split the body into blocks of size cacheBlockSize.`
`273`	`273`	`// If the last block is smaller than cacheBlockSize, it will be ignored.`
`274`	`274`	`res := make([]BlockHash, 0, 1+len(userInput)/cacheBlockSize)`
`275`	`275`	`// Add the model to the first block hash so that different models have different hashes even with the same body.`