Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

mlx: respect tokenizer add_bos_token setting in pipeline (#15185)

Daniel Hiltgen4d14b0ff92cc
diff --git a/x/mlxrunner/pipeline.go b/x/mlxrunner/pipeline.go
index d98d25ccd..4dcfad01d 100644
--- a/x/mlxrunner/pipeline.go
+++ b/x/mlxrunner/pipeline.go
@@ -55,7 +55,7 @@ func (r *Runner) TextGenerationPipeline(request Request) error {
slog.Info("peak memory", "size", mlx.PrettyBytes(mlx.PeakMemory()))
}()
- inputs := r.Tokenizer.Encode(request.Prompt, true)
+ inputs := r.Tokenizer.Encode(request.Prompt, r.Tokenizer.AddBOS())
if len(inputs) == 0 {
return errors.New("empty prompt")
}