do not cache prompt (#2018)

- prompt cache causes inferance to hang after some time
2024-01-16 13:48:05 -05:00 · 2024-01-16 13:48:05 -05:00 · a897e833b8
commit a897e833b8
parent eef50accb4
1 changed files with 0 additions and 1 deletions
--- 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" {