highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-09-27 19:57:05 +02:00
Code Issues Packages Projects Releases Wiki Activity

do not cache prompt (#2018)

Browse Source 
- prompt cache causes inferance to hang after some time
This commit is contained in:
Bruce MacDonald
2024-01-16 13:48:05 -05:00
committed by GitHub
parent eef50accb4
commit a897e833b8
1 changed files with 0 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
llm/dyn_ext_server.go
View File

@@ -181,7 +181,6 @@ func (llm *dynExtServer) Predict(ctx context.Context, predict PredictOpts, fn fu
"seed": predict.Options.Seed, "seed": predict.Options.Seed,
"stop": predict.Options.Stop, "stop": predict.Options.Stop,
"image_data": imageData, "image_data": imageData,
"cache_prompt": true,
} }
if predict.Format == "json" { if predict.Format == "json" {