highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-08-03 20:22:57 +02:00
Code Issues Packages Projects Releases Wiki Activity

sched: Lift parallel restriction for multimodal models except mllama

Browse Source 
The Go runner does not have a problem with supporting parallel
requests for most multimodal models. Now that we won't be potentially
falling back to server.cpp, this restriction can be lifted.

However, the new mllama model can't support parallel requests, so we
will need to keep a restriction for that.
This commit is contained in:
Jesse Gross
2024-10-30 17:09:42 -07:00
committed by Jesse Gross
parent 9d71bcc3e2
commit 6cd566872b
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
server/sched.go
View File

@@ -130,11 +130,11 @@ func (s *Scheduler) processPending(ctx context.Context) {
continue
}
numParallel := int(envconfig.NumParallel())
// TODO (jmorganca): multimodal models don't support parallel yet
// TODO (jmorganca): mllama doesn't support parallel yet
// see https://github.com/ollama/ollama/issues/4165
if len(pending.model.ProjectorPaths) > 0 && numParallel != 1 {
if checkMllamaModelFamily(pending.model) && numParallel != 1 {
numParallel = 1
slog.Warn("multimodal models don't support parallel requests yet")
slog.Warn("mllama doesn't support parallel requests yet")
}
for {