Xinference[mlx] fish audio Hydra error:

[twilwa]

System Info / 系統信息

MacOS Sequoia
M3 MAX 128gb
pyenv, python 3.10
installed via pipx

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

• docker / docker
• pip install / 通过 pip install 安装
• installation from source / 从源码安装

Version info / 版本信息

xinference[mlx]

The command used to start Xinference / 用以启动 xinference 的命令

xinference-local

Reproduction / 复现过程

launch model FishSpeech-1.4

Expected behavior / 期待表现

model launches normally.

error:

2024-12-19 17:02:34,019 xinference.model.audio.fish_speech 70094 INFO Llama model loaded, loading VQ-GAN model...
2024-12-19 17:02:34,461 xinference.core.worker 69626 ERROR Failed to load model FishSpeech-1.4-0
Traceback (most recent call last):
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/worker.py", line 897, in launch_builtin_model
await model_ref.load()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 231, in send
return self._process_result_message(result)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 370, in _run_coro
return await coro
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar/core.pyx", line 558, in on_receive
raise ex
File "xoscar/core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar/core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar/core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/model.py", line 414, in load
self._model.load()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/model/audio/fish_speech.py", line 99, in load
self._model = load_decoder_model(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/model/audio/../../thirdparty/fish_speech/tools/vqgan/inference.py", line 25, in load_model
model = instantiate(cfg)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 226, in instantiate
return instantiate_node(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 342, in instantiate_node
value = instantiate_node(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 333, in instantiate_node
target = _resolve_target(node.get(_Keys.TARGET), full_key)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 139, in _resolve_target
raise InstantiationException(msg) from e
hydra.errors.InstantiationException: [address=127.0.0.1:50299, pid=70094] Error locating target 'fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize', set env var HYDRA_FULL_ERROR=1 to see chained exception.
full_key: quantizer
2024-12-19 17:02:34,510 xinference.core.worker 69626 ERROR [request 129545d6-be6e-11ef-8c73-26d3ab4be478] Leave launch_builtin_model, error: [address=127.0.0.1:50299, pid=70094] Error locating target 'fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize', set env var HYDRA_FULL_ERROR=1 to see chained exception.
full_key: quantizer, elapsed time: 10 s
Traceback (most recent call last):
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/utils.py", line 90, in wrapped
ret = await func(*args, **kwargs)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/worker.py", line 897, in launch_builtin_model
await model_ref.load()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 231, in send
return self._process_result_message(result)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 370, in _run_coro
return await coro
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar/core.pyx", line 558, in on_receive
raise ex
File "xoscar/core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar/core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar/core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/model.py", line 414, in load
self._model.load()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/model/audio/fish_speech.py", line 99, in load
self._model = load_decoder_model(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/model/audio/../../thirdparty/fish_speech/tools/vqgan/inference.py", line 25, in load_model
model = instantiate(cfg)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 226, in instantiate
return instantiate_node(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 342, in instantiate_node
value = instantiate_node(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 333, in instantiate_node
target = _resolve_target(node.get(_Keys.TARGET), full_key)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 139, in _resolve_target
raise InstantiationException(msg) from e
hydra.errors.InstantiationException: [address=127.0.0.1:50299, pid=70094] Error locating target 'fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize', set env var HYDRA_FULL_ERROR=1 to see chained exception.
full_key: quantizer
2024-12-19 17:02:34,638 xinference.api.restful_api 69620 ERROR [address=127.0.0.1:50299, pid=70094] Error locating target 'fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize', set env var HYDRA_FULL_ERROR=1 to see chained exception.
full_key: quantizer
Traceback (most recent call last):
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/api/restful_api.py", line 1002, in launch_model
model_uid = await (await self._get_supervisor_ref()).launch_builtin_model(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 231, in send
return self._process_result_message(result)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 370, in _run_coro
return await coro
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar/core.pyx", line 558, in on_receive
raise ex
File "xoscar/core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar/core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar/core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/supervisor.py", line 1041, in launch_builtin_model
await _launch_model()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/supervisor.py", line 1005, in _launch_model
await _launch_one_model(rep_model_uid)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/supervisor.py", line 984, in _launch_one_model
await worker_ref.launch_builtin_model(
File "xoscar/core.pyx", line 284, in __pyx_actor_method_wrapper
async with lock:
File "xoscar/core.pyx", line 287, in xoscar.core.__pyx_actor_method_wrapper
result = await result
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/utils.py", line 90, in wrapped
ret = await func(*args, **kwargs)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/worker.py", line 897, in launch_builtin_model
await model_ref.load()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 231, in send
return self._process_result_message(result)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/context.py", line 102, in _process_result_message
raise message.as_instanceof_cause()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 667, in send
result = await self._run_coro(message.message_id, coro)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/backends/pool.py", line 370, in _run_coro
return await coro
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xoscar/api.py", line 384, in on_receive
return await super().on_receive(message) # type: ignore
File "xoscar/core.pyx", line 558, in on_receive
raise ex
File "xoscar/core.pyx", line 520, in xoscar.core._BaseActor.on_receive
async with self._lock:
File "xoscar/core.pyx", line 521, in xoscar.core._BaseActor.on_receive
with debug_async_timeout('actor_lock_timeout',
File "xoscar/core.pyx", line 526, in xoscar.core._BaseActor.on_receive
result = await result
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/core/model.py", line 414, in load
self._model.load()
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/model/audio/fish_speech.py", line 99, in load
self._model = load_decoder_model(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/xinference/model/audio/../../thirdparty/fish_speech/tools/vqgan/inference.py", line 25, in load_model
model = instantiate(cfg)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 226, in instantiate
return instantiate_node(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 342, in instantiate_node
value = instantiate_node(
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 333, in instantiate_node
target = _resolve_target(node.get(_Keys.TARGET), full_key)
File "/Users/anon/.local/pipx/venvs/xinference/lib/python3.10/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 139, in _resolve_target
raise InstantiationException(msg) from e
hydra.errors.InstantiationException: [address=127.0.0.1:50299, pid=70094] Error locating target 'fish_speech.models.vqgan.modules.fsq.DownsampleFiniteScalarQuantize', set env var HYDRA_FULL_ERROR=1 to see chained exception.
full_key: quantizer

[qinxuye]

@codingl2k1 Do you have any clue?

[codingl2k1]

Which version of xinference are you using? I can't reproduce it. Please run pip show xinference to get the version info.

[twilwa]

1.1.0
~ via 🐍 v3.10.16
➜ xinference --version
xinference, version 1.1.0

~ via 🐍 v3.10.16 took 1s
➜ pipx list
venvs are in /Users/anon/.local/pipx/venvs
apps are exposed on your $PATH at /Users/anon/.local/bin
manual pages are exposed at /Users/anon/.local/share/man
package xinference 1.1.0, installed using Python 3.10.16
- xinference
- xinference-local
- xinference-supervisor
- xinference-worker

[tomasris]

I had that with the original fish speech, try it.
pip install vector-quantize-pytorch