From a897e833b8f772a59675f75cafb8169601e36b7a Mon Sep 17 00:00:00 2001
From: Bruce MacDonald <brucewmacdonald@gmail.com>
Date: Tue, 16 Jan 2024 13:48:05 -0500
Subject: [PATCH] do not cache prompt (#2018)

- prompt cache causes inferance to hang after some time
---
 llm/dyn_ext_server.go | 1 -
 1 file changed, 1 deletion(-)

diff --git a/llm/dyn_ext_server.go b/llm/dyn_ext_server.go
index 797222c5..fa0d7750 100644
--- a/llm/dyn_ext_server.go
+++ b/llm/dyn_ext_server.go
@@ -181,7 +181,6 @@ func (llm *dynExtServer) Predict(ctx context.Context, predict PredictOpts, fn fu
 		"seed":              predict.Options.Seed,
 		"stop":              predict.Options.Stop,
 		"image_data":        imageData,
-		"cache_prompt":      true,
 	}
 
 	if predict.Format == "json" {