matt/ollama37
1
0
Fork 0
mirror of https://github.com/dogkeeper886/ollama37.git synced 2025-12-11 08:17:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3566 from dhiltgen/more_time

Browse Source 
Handle very slow model loads
This commit is contained in:
Daniel Hiltgen
2024-04-09 16:53:49 -07:00
committed by GitHub
parent c03f0e3c3d c5ff443b9f
commit 4c7db6b7e9
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
llm/server.go
View File

@@ -383,7 +383,8 @@ func (s *LlamaServer) Ping(ctx context.Context) error {
func (s *LlamaServer) waitUntilRunning() error { func (s *LlamaServer) waitUntilRunning() error {
start := time.Now() start := time.Now()
expiresAt := time.Now().Add(3 * time.Minute) // be generous with timeout, large models can take a while to load // TODO we need to wire up a better way to detect hangs during model load and startup of the server
expiresAt := time.Now().Add(10 * time.Minute) // be generous with timeout, large models can take a while to load
ticker := time.NewTicker(50 * time.Millisecond) ticker := time.NewTicker(50 * time.Millisecond)
defer ticker.Stop() defer ticker.Stop()