fix: filter_fn returns True to quantize, not skip

2026-07-18 20:38:15 +08:00 · 2026-07-10 12:10:46 +08:00 · 2026-07-10 12:10:46 +08:00 · 015e8a2676
commit 015e8a2676
parent 2d0bb38f4f
1 changed files with 1 additions and 1 deletions
--- a/comfy/quantization/torchao/quantize.py
+++ b/comfy/quantization/torchao/quantize.py
@ -24,7 +24,7 @@ def quantize_model(
        model: PyTorch model to quantize.
        group_size: Quantization group size (32/64/128/256).
        filter_fn: Optional callable(module, name) → bool.
-                   Return True to skip that module.
+                   Return True to quantize that module.

    Returns:
        Same model (quantized in-place).