From f8a48df24dc375d50285d879542442e26d88a495 Mon Sep 17 00:00:00 2001 From: Parafee41 Date: Fri, 12 Jun 2026 07:05:24 +0800 Subject: [PATCH] llm: decouple prompt caching from context shift (#16639) This PR separates prompt caching from the public shift request option for native llama-server requests. Previously, shift controlled two different mechanisms: context shifting / overflow behavior per-request llama-server cache_prompt That meant callers could not request shift: false without also disabling prompt caching. Fixes #16635 --- llm/llama_server.go | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/llm/llama_server.go b/llm/llama_server.go index 85701351f..c2bb119f5 100644 --- a/llm/llama_server.go +++ b/llm/llama_server.go @@ -1395,7 +1395,7 @@ func (s *llamaServerRunner) Completion(ctx context.Context, req CompletionReques lsReq := llamaServerCompletionRequest{ Prompt: prompt, Stream: true, - CachePrompt: req.Shift, + CachePrompt: true, NPredict: req.Options.NumPredict, NKeep: req.Options.NumKeep, Temperature: req.Options.Temperature, @@ -1984,7 +1984,7 @@ func (s *llamaServerRunner) llamaServerChatRequest(req ChatRequest, stream bool) body := map[string]any{ "messages": messages, "stream": stream, - "cache_prompt": req.Shift, + "cache_prompt": true, "n_predict": req.Options.NumPredict, "n_keep": req.Options.NumKeep, "temperature": req.Options.Temperature,