"docs/vscode:/vscode.git/clone" did not exist on "b215776f2d4d31c160538dccdbfe7c827d1d3e88"
Commit f5fd7cc1 authored by Jesse Gross's avatar Jesse Gross Committed by Michael Yang
Browse files

server: Minimum context length for gptoss

This model requires a minimum context length of 8192 to function
effectively. Users can set higher values through all normal mechanisms
but lower values will be silently reset.
parent 6a68a17c
......@@ -112,6 +112,11 @@ func (s *Server) scheduleRunner(ctx context.Context, name string, caps []model.C
return nil, nil, nil, err
}
// This model requires a minimum context to function effectively
if slices.Contains(model.Config.ModelFamilies, "gptoss") {
opts.NumCtx = max(opts.NumCtx, 8192)
}
runnerCh, errCh := s.sched.GetRunner(ctx, model, opts, keepAlive)
var runner *runnerRef
select {
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment