From 2837225dc7fe6fec740fe9e2caf4078cd7468fee Mon Sep 17 00:00:00 2001 From: rltakashige Date: Thu, 29 Jan 2026 17:08:38 +0000 Subject: [PATCH] Load pipeline layers sequentially (#1329) ## Motivation Slightly annoyed by needing this change, but same story as for tensor loading... --- src/exo/worker/engines/mlx/auto_parallel.py | 3 +++ 1 file changed, 3 insertions(+) diff --git a/src/exo/worker/engines/mlx/auto_parallel.py b/src/exo/worker/engines/mlx/auto_parallel.py index ff2052fb..84ed1f29 100644 --- a/src/exo/worker/engines/mlx/auto_parallel.py +++ b/src/exo/worker/engines/mlx/auto_parallel.py @@ -201,6 +201,9 @@ def pipeline_auto_parallel( device_rank, world_size = model_shard_meta.device_rank, model_shard_meta.world_size layers = layers[start_layer:end_layer] + for layer in layers: + mx.eval(layer) # type: ignore + layers[0] = PipelineFirstLayer(layers[0], device_rank, group=group) layers[-1] = PipelineLastLayer( layers[-1],