From 1d193f58bb30eb42cdf8bdac6ff1b0f2e08e90c9 Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sun, 5 Jul 2026 12:07:31 +0000
Subject: [PATCH] Drop the now-redundant second-expert group offload on the
 A14B load

After the upstream cascade generalised _apply_group_offload to stream every
DiT it finds on the pipe (transformer AND transformer_2), apply_memory_plan's
group tier already block-streams both A14B experts, and model/sequential
offload hook every top-level module. The explicit per-expert pass this branch
added is therefore redundant: on a real group-tier load it re-registers the
group-offload hooks transformer_2 already carries, which diffusers rejects with
a duplicate-hook ValueError. That was swallowed by the helper's try/except and
surfaced as a misleading "second expert stays resident" warning even though the
expert was in fact streamed. Remove the pass and document why MoE needs none.
---
 studio/backend/core/inference/video.py | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/studio/backend/core/inference/video.py b/studio/backend/core/inference/video.py
index 40210c0fb7..9a3a1d82e0 100644
--- a/studio/backend/core/inference/video.py
+++ b/studio/backend/core/inference/video.py
@@ -1004,18 +1004,12 @@ class VideoBackend:
             clear_gpu_cache()
             raise RuntimeError("Video load was cancelled or superseded.")
         offload_policy, vae_tiling = apply_memory_plan(pipe, plan, device = device, logger = logger)
-        if offload_policy == "group" and len(views) > 1:
-            # Group offload streams only ``pipe.transformer``; the second expert would
-            # otherwise sit resident (~57 GB bf16 on the A14B) and defeat the tier.
-            # model/sequential offload hook every top-level module, so only group needs
-            # this. Applied through the view so the helper streams transformer_2.
-            from .diffusion_memory import _apply_group_offload
-            for view in views[1:]:
-                if not _apply_group_offload(view, device, logger):
-                    logger.warning(
-                        "video.memory: group offload did not engage on the second "
-                        "expert; it stays resident"
-                    )
+        # A dual-DiT MoE pipe (Wan2.2-A14B) needs no extra per-expert offload pass here:
+        # apply_memory_plan's group tier (_apply_group_offload) already block-streams every
+        # DiT it finds on the pipe -- transformer AND transformer_2 -- and model/sequential
+        # offload hook every top-level module, so the second expert is covered under all tiers.
+        # A second _apply_group_offload on transformer_2 would re-register the group-offload
+        # hooks it already carries, which diffusers rejects with a duplicate-hook ValueError.
         if not vae_tiling:
             # Decode of a whole clip is the video memory peak; tiling is near-free
             # in quality and keeps the decode bounded, so it is always on.