diff --git a/src/exo/worker/engines/mlx/generator/generate.py b/src/exo/worker/engines/mlx/generator/generate.py index 5af73e42..9501831a 100644 --- a/src/exo/worker/engines/mlx/generator/generate.py +++ b/src/exo/worker/engines/mlx/generator/generate.py @@ -298,6 +298,9 @@ def mlx_generate( ) max_stop_len = max((len(s) for s in stop_sequences), default=0) + logger.info("Ready to prefill") + mx_barrier(group) + # Prefill cache with all tokens except the last one prefill_tps, prefill_tokens, ssm_snapshots_list = prefill( model,