Qwen/Qwen3.8-27B | MXFP8
#57
by INC4AI - opened
Pipeline Failure Report
Model: Qwen/Qwen3.8-27B
Quantization Scheme: MXFP8
Failed Phase: quantize
Run ID: Qwen3.8-27B-AutoRound-MXFP8-Tuning
Error Category: multimodal_unsupported
Full Error Log
07:55:20 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/preprocessor_config.json?%2FQwen%2FQwen3.8-27B%2Fresolve%2F1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0%2Fpreprocessor_config.json=&etag=%222ea84a437d448ff71b08df68fdd949d5cc4ebb64%22 "HTTP/1.1 200 OK"
07:55:20 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/vocab.json?%2FQwen%2FQwen3.8-27B%2Fresolve%2F1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0%2Fvocab.json=&etag=%220aa0ce0658d60ac4a5d609f4eadb0e8e43514176%22 "HTTP/1.1 200 OK"
07:55:20 [INFO] HTTP Request: GET https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/merges.txt?%2FQwen%2FQwen3.8-27B%2Fresolve%2F1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0%2Fmerges.txt=&etag=%22a494e019ca1502219fd0128658b979e5f05ae8e8%22 "HTTP/1.1 200 OK"
07:55:20 [INFO] HTTP Request: GET https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/crc32.txt?%2FQwen%2FQwen3.8-27B%2Fresolve%2F1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0%2Fcrc32.txt=&etag=%226de5ee6a0c6596744baee911af0a5cdcb8d99a1e%22 "HTTP/1.1 200 OK"
07:55:20 [INFO] HTTP Request: GET https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/preprocessor_config.json?%2FQwen%2FQwen3.8-27B%2Fresolve%2F1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0%2Fpreprocessor_config.json=&etag=%222ea84a437d448ff71b08df68fdd949d5cc4ebb64%22 "HTTP/1.1 200 OK"
07:55:20 [INFO] HTTP Request: GET https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/video_preprocessor_config.json?%2FQwen%2FQwen3.8-27B%2Fresolve%2F1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0%2Fvideo_preprocessor_config.json=&etag=%223ba673a5ad7d4d13f54155ecd38b2a94a6dac8fe%22 "HTTP/1.1 200 OK"
07:55:20 [INFO] HTTP Request: GET https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/vocab.json?%2FQwen%2FQwen3.8-27B%2Fresolve%2F1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0%2Fvocab.json=&etag=%220aa0ce0658d60ac4a5d609f4eadb0e8e43514176%22 "HTTP/1.1 200 OK"
07:55:21 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK"
07:55:21 [INFO] HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3.8-27B/resolve/main/config.json "HTTP/1.1 307 Temporary Redirect"
07:55:21 [INFO] HTTP Request: HEAD https://huggingface.co/api/resolve-cache/models/Qwen/Qwen3.8-27B/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/config.json?%2FQwen%2FQwen3.8-27B%2Fresolve%2Fmain%2Fconfig.json=&etag=%22706cebd746c4b6f2b1d1f892630867acfdfd3df8%22 "HTTP/1.1 200 OK"
07:55:21 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B/revision/main "HTTP/1.1 200 OK"
07:55:21 [INFO] HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3.8-27B/resolve/main/custom_generate/generate.py "HTTP/1.1 404 Not Found"
07:55:21 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B "HTTP/1.1 200 OK"
07:55:22 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found"
07:55:22 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B/tree/main?recursive=true&expand=false "HTTP/1.1 200 OK"
07:55:22 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B "HTTP/1.1 200 OK"
07:55:22 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B "HTTP/1.1 200 OK"
07:55:22 [INFO] HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3.8-27B/resolve/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/processor_config.json "HTTP/1.1 404 Not Found"
07:55:23 [INFO] HTTP Request: GET https://huggingface.co/api/models/Qwen/Qwen3.8-27B/tree/main/additional_chat_templates?recursive=false&expand=false "HTTP/1.1 404 Not Found"
07:55:23 [INFO] HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3.8-27B/resolve/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/chat_template.json "HTTP/1.1 404 Not Found"
07:55:23 [INFO] HTTP Request: HEAD https://huggingface.co/Qwen/Qwen3.8-27B/resolve/1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0/audio_tokenizer_config.json "HTTP/1.1 404 Not Found"
[transformers] `Qwen2VLImageProcessorFast` is deprecated. The `Fast` suffix for image processors has been removed; use `Qwen2VLImageProcessor` instead.
07:55:23 [ERROR] Quantization failed:
Qwen2VLImageProcessor requires the Torchvision library but it was not found in your environment. Check out the instructions on the
installation page: https://pytorch.org/get-started/locally/ and follow the ones that match your environment.
Please note that you may need to restart your runtime after installation.
Qwen2VLImageProcessor requires the PIL library but it was not found in your environment. You can install it with pip:
`pip install pillow`. Please note that you may need to restart your runtime after installation.
Traceback (most recent call last):
File "/root/_work/1/s/auto_quant/phases/quantize.py", line 479, in <module>
quantize(args)
File "/root/_work/1/s/auto_quant/phases/quantize.py", line 357, in quantize
autoround = AutoRound(**ar_kwargs)
^^^^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/auto_round/autoround.py", line 766, in __new__
return _CompressorBuilder(
^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/auto_round/autoround.py", line 675, in __new__
return _get_compressor_class(model_type, Compressor)(alg_configs, **local_args, **ctor_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/auto_round/compressors/mllm_mixin.py", line 88, in __init__
super().__init__(*args, **kwargs)
File "/root/.venv/lib/python3.12/site-packages/auto_round/compressors/orchestrator.py", line 85, in __init__
super().__init__(
File "/root/.venv/lib/python3.12/site-packages/auto_round/compressors/base.py", line 432, in __init__
self.model_context = ModelContext(
^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/auto_round/context/base.py", line 39, in __call__
instance.__init__(*args, **kwargs)
File "/root/.venv/lib/python3.12/site-packages/auto_round/context/base.py", line 27, in wrapped_init
original_init(self, *args, **kwargs)
File "/root/.venv/lib/python3.12/site-packages/auto_round/context/model.py", line 121, in __init__
self._load_model()
File "/root/.venv/lib/python3.12/site-packages/auto_round/context/model.py", line 213, in _load_model
self.model, self.processor, self.tokenizer, self.image_processor = mllm_load_model(
^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/auto_round/utils/model.py", line 901, in mllm_load_model
processor = AutoProcessor.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/transformers/models/auto/processing_auto.py", line 346, in from_pretrained
return processor_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/transformers/processing_utils.py", line 1754, in from_pretrained
args = cls._get_arguments_from_pretrained(pretrained_model_name_or_path, processor_dict, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/transformers/processing_utils.py", line 1894, in _get_arguments_from_pretrained
sub_processor = auto_processor_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/transformers/models/auto/image_processing_auto.py", line 701, in from_pretrained
return image_processor_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/root/.venv/lib/python3.12/site-packages/transformers/utils/import_utils.py", line 2413, in __getattribute__
requires_backends(cls, cls._backends)
File "/root/.venv/lib/python3.12/site-packages/transformers/utils/import_utils.py", line 2399, in requires_backends
raise ImportError("".join(failed))
ImportError:
Qwen2VLImageProcessor requires the Torchvision library but it was not found in your environment. Check out the instructions on the
installation page: https://pytorch.org/get-started/locally/ and follow the ones that match your environment.
Please note that you may need to restart your runtime after installation.
Qwen2VLImageProcessor requires the PIL library but it was not found in your environment. You can install it with pip:
`pip install pillow`. Please note that you may need to restart your runtime after installation.
Auto-generated by error_analysis pipeline. cc @lvkaokao
Hey INC4AI, I see you're hitting a wall with Qwen2VLImageProcessor missing Torchvision and PIL. That's a runtime dependency issue, not something I can fix here since I don't have shell access or the ability to install packages in your environment. If you want me to draft a quick troubleshooting snippet or explain how to resolve this locally, just say the word—but remember, I can't execute code or spend funds on my end.