Qwen3-Next support (#10233)

Co-authored-by: cao1zhg <114661107+cao1zhg@users.noreply.github.com>
Co-authored-by: ispobock <ispobaoke@gmail.com>
Co-authored-by: Binyao Jiang <byjiang1996@gmail.com>
Co-authored-by: hebiao064 <hebiaobuaa@gmail.com>
Co-authored-by: Lifu Huang <lifu.hlf@gmail.com>
Co-authored-by: qingquansong <ustcsqq@gmail.com>
Co-authored-by: Yaoyao Ding <dingyaoyao.cs@gmail.com>
Co-authored-by: Ke Bao <ISPObaoke@163.com>
Co-authored-by: Minglei Zhu <mingleizhu1122@gmail.com>

python/sglang/srt/model_loader/weight_utils.py

@@ -35,6 +35,7 @@ from tqdm.auto import tqdm
 from sglang.srt.configs.load_config import LoadConfig
 from sglang.srt.configs.model_config import ModelConfig
 from sglang.srt.distributed import get_tensor_model_parallel_rank
+from sglang.srt.layers.dp_attention import get_attention_tp_rank
 from sglang.srt.layers.quantization import QuantizationConfig, get_quantization_config
 from sglang.srt.layers.quantization.modelopt_quant import ModelOptFp4Config
 from sglang.srt.utils import print_warning_once
@@ -680,7 +681,7 @@ def sharded_weight_loader(shard_axis: int) -> LoaderFunction:
     """Create a weight loader that shards the weights along the given axis"""
 
     def loader(param: torch.Tensor, loaded_weight: torch.Tensor) -> None:
-        tp_rank = get_tensor_model_parallel_rank()
+        tp_rank = get_attention_tp_rank()
 
         shard_size = param.data.shape[shard_axis]
         start_idx = tp_rank * shard_size