fix qwenvl compressed tensors quantization weight loader (#11914)

Signed-off-by: LHXuuu <xulianhao.xlh@antgroup.com>
Co-authored-by: Peng Zhang <aniz1905@gmail.com>

python/sglang/srt/model_loader/loader.py

@@ -257,6 +257,10 @@ def _initialize_model(
     quant_config = _get_quantization_config(
         model_config, load_config, packed_modules_mapping, remap_prefix
     )
+    hf_to_sglang_mapper = getattr(model_class, "hf_to_sglang_mapper", None)
+    # pass mappings by reference to quant_config
+    if hf_to_sglang_mapper is not None and quant_config is not None:
+        quant_config.apply_sglang_mapper(hf_to_sglang_mapper)
 
     # Build kwargs conditionally
     kwargs = {