matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 00:07:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

runner: remove cache prompt flag from ollama runner (#9826)

Browse Source 
We do not need to bypass the prompt caching in the ollama runner yet, as
only embedding models needed to bypass the prompt caching. When embedding
models are implemented they can skip initializing this cache completely.
This commit is contained in:
Bruce MacDonald
2025-03-17 15:11:15 -07:00
committed by GitHub
parent 364629b8d6
commit 95e271d98f
3 changed files with 130 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
runner/ollamarunner/runner.go
View File

@@ -590,7 +590,7 @@ func (s *Server) completion(w http.ResponseWriter, r *http.Request) {
found := false
for i, sq := range s.seqs {
if sq == nil {
seq.cache, seq.inputs, err = s.cache.LoadCacheSlot(seq.inputs, true)
seq.cache, seq.inputs, err = s.cache.LoadCacheSlot(seq.inputs)
if err != nil {
s.mu.Unlock()
http.Error(w, fmt.Sprintf("Failed to load cache: %v", err), http.StatusInternalServerError)