Verified 40 original paths
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner.py", line 1203, in load_model
    loaded = load_model_with_memory_saver(
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/sgl-workspace/sglang/python/sglang/srt/model_executor/model_runner_components/load_model_utils.py", line 339, in load_model_with_memory_saver
    model = loader.load_model(
            ^^^^^^^^^^^^^^^^^^
  File "/sgl-workspace/sglang/python/sglang/srt/model_loader/loader.py", line 982, in load_model
    model = _initialize_model(
            ^^^^^^^^^^^^^^^^^^
  File "/sgl-workspace/sglang/python/sglang/srt/model_loader/loader.py", line 304, in _initialize_model
    return model_class(**kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
  File "/sgl-workspace/sglang/python/sglang/srt/models/mimo_v2.py", line 1246, in __init__
    self.build_audio_encoder(MiMoAudioEncoderConfig(**audio_config))
  File "/sgl-workspace/sglang/python/sglang/srt/models/mimo_audio.py", line 1252, in build_audio_encoder
    self.projection = AudioProjection(
                      ^^^^^^^^^^^^^^^^
  File "/sgl-workspace/sglang/python/sglang/srt/models/mimo_audio.py", line 947, in __init__
    nn.Linear(self.input_size, self.hidden_size, bias=False),
    ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/sglang/lib/python3.12/site-packages/torch/nn/modules/linear.py", line 109, in __init__
    torch.empty((out_features, in_features), **factory_kwargs)
  File "/opt/sglang/lib/python3.12/site-packages/torch/utils/_device.py", line 122, in __torch_function__
    return func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 128.00 MiB. GPU 1 has a total capacity of 94.97 GiB of which 126.75 MiB is free. Including non-PyTorch memory, this process has 94.84 GiB memory in use. Of the allocated memory 93.84 GiB is allocated by PyTorch, and 49.13 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://docs.pytorch.org/docs/stable/notes/cuda.html#optimizing-memory-usage-with-pytorch-cuda-alloc-conf)

[2026-09-22 02:42:10] Received sigquit from a child process. It usually means the child failed.
[2026-09-22 02:42:10] kill_process_tree called: parent_pid=1, include_parent=True, pid=1
[2026-09-22 02:42:10] kill_process_tree called: parent_pid=1, include_parent=False, pid=1