PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度
fix: support list inputs in diffusion tuning cache (#2346)
Wang, Changc53611fbd8ca
diff --git a/auto_round/compressors/diffusion/tuning_cache.py b/auto_round/compressors/diffusion/tuning_cache.pyindex a3f9b55f4..57581a1c6 100644--- a/auto_round/compressors/diffusion/tuning_cache.py+++ b/auto_round/compressors/diffusion/tuning_cache.py@@ -74,6 +74,9 @@ class DiffusionTuningCache:@classmethoddef create(cls, block, runner, inputs, others, outputs, sampler, iters, budget_gib, device):+ # Single-output blocks (e.g. Wan) pass a tensor list to the next block.+ if isinstance(inputs, list):+ inputs = {"hidden_states": inputs}if runner.batch_size != 1 or not isinstance(inputs, dict) or iters <= 0:return Nonecache = cls()