← back to Exo
Load pipeline layers sequentially (#1329)
2837225dc7fe6fec740fe9e2caf4078cd7468fee · 2026-01-29 17:08:38 +0000 · rltakashige
## Motivation
Slightly annoyed by needing this change, but same story as for tensor
loading...
Files touched
M src/exo/worker/engines/mlx/auto_parallel.py
Diff
commit 2837225dc7fe6fec740fe9e2caf4078cd7468fee
Author: rltakashige <rl.takashige@gmail.com>
Date: Thu Jan 29 17:08:38 2026 +0000
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],
← e4c6a7db nix: add Python packaging with uv2nix
·
back to Exo
·
Treat Swift/Xcode build warnings as errors (#1322) 7cc313b2 →