From 27ae5c335cba438e6198c4fdbabe9a0a85b329b4 Mon Sep 17 00:00:00 2001
From: Bhuvan Prakash <52481324+bhuvanprakash@users.noreply.github.com>
Date: Sun, 30 Nov 2025 09:48:11 +0530
Subject: [PATCH] Fix: prevent load_in_fp8 kwarg from reaching
 Qwen3MoeForCausalLM constructor (Fix #3649) (#3654)

* Fix: remove load_in_fp8 from kwargs to prevent Qwen3Moe init TypeError (Fix #3649)

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
---
 unsloth/models/vision.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/unsloth/models/vision.py b/unsloth/models/vision.py
index 30d381c791..31901b1570 100644
--- a/unsloth/models/vision.py
+++ b/unsloth/models/vision.py
@@ -654,6 +654,8 @@ class FastBaseModel:
 
         raise_handler = RaiseUninitialized()
         if not fast_inference:
+            # Prevent load_in_fp8 from being forwarded into HF internal model loading
+            load_in_fp8 = kwargs.pop("load_in_fp8", None)
             model = auto_model.from_pretrained(
                 model_name,
                 device_map = device_map,