[2025-06-21 19:55:30 DP0 TP7] TpModelWorkerClient hit an exception: Traceback (most recent call last):
  File "/usr/local/src/sglang/python/sglang/srt/managers/tp_worker_overlap_thread.py", line 127, in forward_thread_func
    self.forward_thread_func_()
  File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/src/sglang/python/sglang/srt/managers/tp_worker_overlap_thread.py", line 162, in forward_thread_func_
    self.worker.forward_batch_generation(
  File "/usr/local/src/sglang/python/sglang/srt/managers/tp_worker.py", line 211, in forward_batch_generation
    logits_output, can_run_cuda_graph = self.model_runner.forward(
  File "/usr/local/src/sglang/python/sglang/srt/model_executor/model_runner.py", line 1221, in forward
    output = self._forward_raw(
  File "/usr/local/src/sglang/python/sglang/srt/model_executor/model_runner.py", line 1250, in _forward_raw
    ret = self.forward_extend(
  File "/usr/local/src/sglang/python/sglang/srt/model_executor/model_runner.py", line 1189, in forward_extend
    return self.model.forward(
  File "/usr/local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
    return func(*args, **kwargs)
  File "/usr/local/src/sglang/python/sglang/srt/models/deepseek_v2.py", line 1764, in forward
    hidden_states = self.model(input_ids, positions, forward_batch, input_embeds)
  File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/src/sglang/python/sglang/srt/models/deepseek_v2.py", line 1657, in forward
    hidden_states, residual = layer(
  File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1751, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/usr/local/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1762, in _call_impl
    return forward_call(*args, **kwargs)
  File "/usr/local/src/sglang/python/sglang/srt/models/deepseek_v2.py", line 1491, in forward
    hidden_states, residual = self.layer_communicator.prepare_attn(
  File "/usr/local/src/sglang/python/sglang/srt/layers/communicator.py", line 191, in prepare_attn
    hidden_states = self._communicate_simple_fn(
  File "/usr/local/src/sglang/python/sglang/srt/layers/communicator.py", line 294, in _scattered_to_tp_attn_full
    attn_tp_all_gather(
  File "/usr/local/src/sglang/python/sglang/srt/layers/dp_attention.py", line 313, in attn_tp_all_gather
    return get_attention_tp_group().all_gather(input_, tensor_list=output_list)
TypeError: GroupCoordinator.all_gather() got an unexpected keyword argument 'tensor_list'```






### Reproduction

## start cmd

```python -m sglang.launch_server --model-path /work/models/ --port 30000 --trust-remote --host 0.0.0.0 --disable-radix-cache --init-expert-location /home/aiges/tuned/attachment_ep_statistics/prefill_in1024.json --ep-dispatch-algorithm dynamic --eplb-algorithm deepseek --deepep-config /home/aiges/tuned/tuned_8sms.json --enable-dp-lm-head --chunked-prefill-size 262144 --max-prefill-tokens 32768 --tp 16 --dp-size 2 --page-size 64 --enable-dp-attention --context-length 32768 --max-running-requests 1024 --mem-fraction-static 0.83 --enable-deepep-moe --deepep-mode normal --ep-num-redundant-experts 32 --moe-dense-tp-size 1 --disaggregation-ib-device mlx5_bond_0,mlx5_bond_1,mlx5_bond_2,mlx5_bond3 --enable-metrics --disaggregation-mode prefill --nnodes 2 --dist-init-addr xdeepseekv3-lws-mtp-main-prefill-0.xdeepseekv3-lws-mtp-main-prefill.aiservice:20102 --node-rank 0```

### Environment

main branch