| 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.
|
| import pynvml # type: ignore[import]
|
| 2025-11-23 16:35:08.739 | INFO | __main__:<module>:104 - STRATEGY - cpu fp16
|
| 2025-11-23 16:35:08.740 | INFO | __main__:<module>:109 - Load Model - rwkv7-g1a-0.1b-20250728-ctx4096
|
| 2025-11-23 16:35:09.724 | INFO | __main__:<module>:117 - Load Model - Path - models\rwkv7-g1a-0.1b-20250728-ctx4096.pth
|
| 2025-11-23 16:35:09.724 | INFO | __main__:<module>:133 - Load Model - Loading `rwkv7-g1a-0.1b-20250728-ctx4096`
|
| 2025-11-23 16:35:15.073 | INFO | __main__:<module>:151 - Load Model - DEFALUT_MODEL_NAME is `rwkv7-g1a-0.1b-20250728-ctx4096`
|
| 2025-11-23 16:35:15.074 | INFO | __main__:<module>:152 - Load Model - DEFAULT_REASONING_MODEL_NAME is `rwkv7-g1a-0.1b-20250728-ctx4096`
|
| 2025-11-23 16:35:15.080 | INFO | __main__:<module>:746 - dist-frontend not found; skipping static files mount
|
| INFO: Started server process [9328]
|
| INFO: Waiting for application startup.
|
| INFO: Application startup complete.
|
| INFO: Uvicorn running on http://0.0.0.0:7860 (Press CTRL+C to quit)
|
| 2025-11-23 16:35:51.067 | INFO | __main__:chat_completions:698 - [REQ] 7398519686318694400 - {'model': 'rwkv-latest', 'messages': None, 'prompt': 'Who is the current president of France?', 'max_tokens': 50, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': True, 'search_top_k': 3}
|
| 2025-11-23 16:35:51.067 | INFO | __main__:chat_completions:729 - [REQ] 7398519686318694400 - Real - {'model': 'rwkv7-g1a-0.1b-20250728-ctx4096', 'messages': None, 'prompt': 'Who is the current president of France?', 'max_tokens': 50, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': True, 'search_top_k': 3}
|
| 2025-11-23 16:35:53.728 | INFO | __main__:chatResponse:363 - [REQ] 7398519686318694400 - prompt - Who is the current president of France?
|
| 2025-11-23 16:36:09.388 | INFO | __main__:chatResponse:402 - [RES] 7398519686318694400 - {'content': '\nThe current president of France is Emmanuel Macron.', 'finish': 'stop:words:\n\n', 'prefill_len': 9, 'prefill_tps': 1.36, 'gen_len': 6, 'gen_tps': 0.51}
|
| 2025-11-23 16:36:52.165 | INFO | __main__:chat_completions:698 - [REQ] 7398519942582280192 - {'model': 'rwkv7-g1a-0.1b-20250728-ctx4096:thinking', 'messages': None, 'prompt': 'Summarize the first paragraph from the search about Python programming', 'max_tokens': 60, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': True, 'search_top_k': 2}
|
| 2025-11-23 16:36:52.165 | INFO | __main__:chat_completions:729 - [REQ] 7398519942582280192 - Real - {'model': 'rwkv7-g1a-0.1b-20250728-ctx4096', 'messages': None, 'prompt': 'Summarize the first paragraph from the search about Python programming', 'max_tokens': 60, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': True, 'search_top_k': 2}
|
| 2025-11-23 16:36:54.650 | INFO | __main__:chatResponse:363 - [REQ] 7398519942582280192 - prompt - Summarize the first paragraph from the search about Python programming
|
| 2025-11-23 16:38:03.778 | INFO | __main__:chatResponse:402 - [RES] 7398519942582280192 - {'content': ' <think.\nThe first paragraph of the search is about Python programming. It talks about how to use Python for data analysis and machine learning. The second paragraph is about how to use Python for web development. It talks about how to use Python for creating websites and applications. The third', 'finish': 'length', 'prefill_len': 13, 'prefill_tps': 1.65, 'gen_len': 56, 'gen_tps': 0.88}
|
| 2025-11-23 16:38:05.030 | INFO | __main__:chat_completions:698 - [REQ] 7398520248166686720 - {'model': 'rwkv7-g1a-0.1b-20250728-ctx4096:thinking', 'messages': None, 'prompt': 'Tell me a short summary of Python programming', 'max_tokens': 50, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': True, 'search_top_k': 2}
|
| 2025-11-23 16:38:05.033 | INFO | __main__:chat_completions:729 - [REQ] 7398520248166686720 - Real - {'model': 'rwkv7-g1a-0.1b-20250728-ctx4096', 'messages': None, 'prompt': 'Tell me a short summary of Python programming', 'max_tokens': 50, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': True, 'search_top_k': 2}
|
| 2025-11-23 16:38:06.800 | INFO | __main__:chatResponse:363 - [REQ] 7398520248166686720 - prompt - Tell me a short summary of Python programming
|
| 2025-11-23 16:38:24.585 | INFO | __main__:chatResponse:402 - [RES] 7398520248166686720 - {'content': ' <think and how it can be used to solve problems.', 'finish': 'stop:words:\n\n', 'prefill_len': 9, 'prefill_tps': 1.55, 'gen_len': 6, 'gen_tps': 0.44}
|
| 2025-11-23 16:42:18.982 | INFO | __main__:chat_completions:698 - [REQ] 7398521313352130560 - {'model': 'rwkv-latest', 'messages': None, 'prompt': 'What is two plus three times four?', 'max_tokens': 32, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': False, 'search_top_k': 3}
|
| 2025-11-23 16:42:18.982 | INFO | __main__:chat_completions:729 - [REQ] 7398521313352130560 - Real - {'model': 'rwkv7-g1a-0.1b-20250728-ctx4096', 'messages': None, 'prompt': 'What is two plus three times four?', 'max_tokens': 32, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': False, 'search_top_k': 3}
|
| 2025-11-23 16:42:18.982 | INFO | __main__:chatResponse:363 - [REQ] 7398521313352130560 - prompt - What is two plus three times four?
|
| 2025-11-23 16:42:56.030 | INFO | __main__:chatResponse:402 - [RES] 7398521313352130560 - {'content': '\n100\nWhat is the difference between 0.9 and 0.8?\n0.2\nWhat is the sum of', 'finish': 'length', 'prefill_len': 9, 'prefill_tps': 2.17, 'gen_len': 28, 'gen_tps': 0.85}
|
| 2025-11-23 16:44:08.178 | INFO | __main__:chat_completions:698 - [REQ] 7398521771353350144 - {'model': 'rwkv-latest', 'messages': None, 'prompt': 'What is two plus three times four?', 'max_tokens': 32, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': False, 'search_top_k': 3}
|
| 2025-11-23 16:44:08.179 | INFO | __main__:chat_completions:729 - [REQ] 7398521771353350144 - Real - {'model': 'rwkv7-g1a-0.1b-20250728-ctx4096', 'messages': None, 'prompt': 'What is two plus three times four?', 'max_tokens': 32, 'temperature': None, 'top_p': None, 'presence_penalty': None, 'count_penalty': None, 'penalty_decay': None, 'stream': False, 'state_name': None, 'include_usage': False, 'stop': ['\n\n'], 'stop_tokens': [0], 'web_search': False, 'search_top_k': 3}
|
| 2025-11-23 16:44:08.179 | INFO | __main__:chatResponse:363 - [REQ] 7398521771353350144 - prompt - What is two plus three times four?
|
| 2025-11-23 16:44:45.828 | INFO | __main__:chatResponse:402 - [RES] 7398521771353350144 - {'content': '\nTwo plus three times four is eight.\nWhat is the sum of the digits of two-digit numbers?\nThe sum of', 'finish': 'length', 'prefill_len': 9, 'prefill_tps': 2.28, 'gen_len': 28, 'gen_tps': 0.83}
|
| |
