Xorbits

/

chatglm3-6B-GGML

like 8

pip install xinference[ggml]>=0.4.3
xinference -p 9997

/usr/local/lib/python3.10/dist-packages/xinference/deploy/cmdline.py:130: DeprecationWarning: Starting a local 'xinference' cluster via the 'xinference' command line is deprecated and will be removed in a future release. Please use the new 'xinference-local' command.
  warnings.warn(
Process Process-1:
Traceback (most recent call last):
  File "/usr/local/lib/python3.10/dist-packages/cupy/__init__.py", line 18, in <module>
    from cupy import _core  # NOQA
  File "/usr/local/lib/python3.10/dist-packages/cupy/_core/__init__.py", line 3, in <module>
    from cupy._core import core  # NOQA
ImportError: libcuda.so.1: cannot open shared object file: No such file or directory

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/usr/lib/python3.10/multiprocessing/process.py", line 314, in _bootstrap
    self.run()
  File "/usr/lib/python3.10/multiprocessing/process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "/usr/local/lib/python3.10/dist-packages/xinference/deploy/local.py", line 67, in run
    loop.run_until_complete(task)
  File "/usr/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
    return future.result()
  File "/usr/local/lib/python3.10/dist-packages/xinference/deploy/local.py", line 42, in _start_local_cluster
    pool = await create_worker_actor_pool(
  File "/usr/local/lib/python3.10/dist-packages/xinference/deploy/utils.py", line 98, in create_worker_actor_pool
    return await xo.create_actor_pool(
  File "/usr/local/lib/python3.10/dist-packages/xoscar/api.py", line 160, in create_actor_pool
    return await get_backend(scheme).create_actor_pool(
  File "/usr/local/lib/python3.10/dist-packages/xoscar/backends/indigen/backend.py", line 49, in create_actor_pool
    return await create_actor_pool(
  File "/usr/local/lib/python3.10/dist-packages/xoscar/backends/pool.py", line 1549, in create_actor_pool
    pool: MainActorPoolType = await pool_cls.create(
  File "/usr/local/lib/python3.10/dist-packages/xoscar/backends/pool.py", line 1255, in create
    pool: MainActorPoolType = await super().create(config)
  File "/usr/local/lib/python3.10/dist-packages/xoscar/backends/pool.py", line 793, in create
    TypeDispatcher.reload_all_lazy_handlers()
  File "xoscar/_utils.pyx", line 110, in xoscar._utils.TypeDispatcher.reload_all_lazy_handlers
  File "xoscar/_utils.pyx", line 69, in xoscar._utils.TypeDispatcher._reload_lazy_handlers
  File "xoscar/_utils.pyx", line 74, in xoscar._utils.TypeDispatcher._reload_lazy_handlers
  File "/usr/lib/python3.10/importlib/__init__.py", line 126, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1050, in _gcd_import
  File "<frozen importlib._bootstrap>", line 1027, in _find_and_load
  File "<frozen importlib._bootstrap>", line 1006, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 688, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 883, in exec_module
  File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
  File "/usr/local/lib/python3.10/dist-packages/cupy/__init__.py", line 20, in <module>
    raise ImportError(f'''
ImportError: 
================================================================
Failed to import CuPy.

If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.

On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.

Check the Installation Guide for details:
  https://docs.cupy.dev/en/latest/install.html

Original error:
  ImportError: libcuda.so.1: cannot open shared object file: No such file or directory
================================================================

Traceback (most recent call last):
  File "/usr/local/bin/xinference", line 8, in <module>
    sys.exit(cli())
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1157, in __call__
    return self.main(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1078, in main
    rv = self.invoke(ctx)
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1666, in invoke
    rv = super().invoke(ctx)
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 1434, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/usr/local/lib/python3.10/dist-packages/click/core.py", line 783, in invoke
    return __callback(*args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/click/decorators.py", line 33, in new_func
    return f(get_current_context(), *args, **kwargs)
  File "/usr/local/lib/python3.10/dist-packages/xinference/deploy/cmdline.py", line 137, in cli
    start_local_cluster(log_level=log_level, host=host, port=port)
  File "/usr/local/lib/python3.10/dist-packages/xinference/deploy/cmdline.py", line 80, in start_local_cluster
    main(
  File "/usr/local/lib/python3.10/dist-packages/xinference/deploy/local.py", line 83, in main
    raise RuntimeError("Cluster is not available after multiple attempts")
RuntimeError: Cluster is not available after multiple attempts