From 232a631be56899ab34f60a62ba9885d05f993afa Mon Sep 17 00:00:00 2001
From: Disty0 <disty@disty.xyz>
Date: Mon, 11 Aug 2025 23:31:06 +0300
Subject: [PATCH] Use pre-mode quant on custom transformer files

---
 pipelines/generic.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/pipelines/generic.py b/pipelines/generic.py
index d4065cb50..2f634b470 100644
--- a/pipelines/generic.py
+++ b/pipelines/generic.py
@@ -42,8 +42,8 @@ def load_transformer(repo_id, cls_name, load_config={}, subfolder="transformer",
                 local_file,
                 cache_dir=shared.opts.hfcache_dir,
                 **load_args,
+                **quant_args,
             )
-            transformer = model_quant.do_post_load_quant(transformer, allow=quant_type is not None)
         else:
             shared.log.debug(f'Load model: transformer="{repo_id}" cls={cls_name.__name__} quant="{quant_type}" args={load_args}')
             if dtype is not None: