tests/run_chat_response_out.txt

��python.exe : C:\Users\Administrator\Downloads\New folder 
(3)\RWKV\.venv\Lib\site-packages\torch\cuda\__init__.py:63: FutureWarning: The pynvml 
package is deprecated. Please install nvidia-ml-py instead. If you did not install pynvml 
directly, please report this to the maintainers of the package that installed pynvml for 
you.
At line:1 char:52
+ ... oviderPath; & "C:/Users/Administrator/Downloads/New folder (3)/RWKV/. ...
+                 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    + CategoryInfo          : NotSpecified: (C:\Users\Admini...pynvml for you.:String) [] 
   , RemoteException
    + FullyQualifiedErrorId : NativeCommandError
 
  import pynvml  # type: ignore[import]

### RWKV-7 "Goose" enabled ###

2025-11-23 18:07:07.248 | INFO     | app:<module>:116 - STRATEGY - cpu fp16
2025-11-23 18:07:07.248 | INFO     | app:<module>:134 - Load Model - 
rwkv7-g1a-0.1b-20250728-ctx4096
2025-11-23 18:07:08.322 | INFO     | app:<module>:142 - Load Model - Path - 
models\rwkv7-g1a-0.1b-20250728-ctx4096.pth
2025-11-23 18:07:08.322 | INFO     | app:<module>:158 - Load Model - Loading 
`rwkv7-g1a-0.1b-20250728-ctx4096`
SamplerConfig(
    max_tokens=4096,
    temperature=1.0,
    top_p=0.3,
    presence_penalty=0.5,
    count_penalty=0.5,
    penalty_decay=0.996,
    stop=['\n\n'],
    stop_tokens=[0]
)
Loading models\rwkv7-g1a-0.1b-20250728-ctx4096 (cpu fp16)

2025-11-23 18:07:12.250 | INFO     | app:<module>:176 - Load Model - DEFALUT_MODEL_NAME 
is `rwkv7-g1a-0.1b-20250728-ctx4096`
2025-11-23 18:07:12.250 | INFO     | app:<module>:177 - Load Model - 
DEFAULT_REASONING_MODEL_NAME is `rwkv7-g1a-0.1b-20250728-ctx4096`
2025-11-23 18:07:12.252 | INFO     | app:<module>:1013 - dist-frontend not found; 
skipping static files mount
2025-11-23 18:07:14.682 | INFO     | app:chatResponse:454 - [REQ] test123 - prompt - Who 
is the president of France today?
Traceback (most recent call last):
  File "C:\Users\Administrator\Downloads\New folder (3)\RWKV\tests\run_chat_response.py", 
line 11, in <module>
    asyncio.run(test())
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.2800.0_x64_
_qbz5n2kfra8p0\Lib\asyncio\runners.py", line 195, in run
    return runner.run(main)
           ^^^^^^^^^^^^^^^^
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.2800.0_x64_
_qbz5n2kfra8p0\Lib\asyncio\runners.py", line 118, in run
    return self._loop.run_until_complete(task)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.12_3.12.2800.0_x64_
_qbz5n2kfra8p0\Lib\asyncio\base_events.py", line 691, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "C:\Users\Administrator\Downloads\New folder (3)\RWKV\tests\run_chat_response.py", 
line 7, in test
    res = await chatResponse(req, model_state=None, completionId='test123', 
enableReasoning=False)
          
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Administrator\Downloads\New folder (3)\RWKV\app.py", line 467, in 
chatResponse
    out, model_tokens, model_state = await runPrefill(request, prompt, [0], model_state)
                                     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "C:\Users\Administrator\Downloads\New folder (3)\RWKV\app.py", line 255, in 
runPrefill
    raise HTTPException(500, f"Model {request.model} not loaded or pipeline missing")
fastapi.exceptions.HTTPException: 500: Model rwkv-latest not loaded or pipeline missing