[GH-ISSUE #3238] Segmentation fault when starting backend on intel cpu. #13185

New Issue

GiteaMirror · 2026-04-19T19:59:01-05:00

GiteaMirror commented

2026-04-19 19:59:01 -05:00

Originally created by @w-A-L-L-e on GitHub (Jun 17, 2024).
Original GitHub issue: https://github.com/open-webui/open-webui/issues/3238

Bug Report

When starting the backend with ./start.sh there seems to be a problem with the BertTokenizerFast causing a segfault:

Description

Bug Summary:
[Provide a brief but clear summary of the bug]

Steps to Reproduce:
pip install -r requirements.txt
./start.sh

Expected Behavior:
Backend starts up and listens to a port

Actual Behavior:
Backend gives segmentation fault:

OSError: Can't load tokenizer for '/Users/wschrep/.cache/huggingface/hub/models--sentence-transformers--all-MiniLM-L6-v2/snapshots/8b3219a92973c328a8e22fadcfa821b5dc75636a'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure '/Users/wschrep/.cache/huggingface/hub/models--sentence-transformers--all-MiniLM-L6-v2/snapshots/8b3219a92973c328a8e22fadcfa821b5dc75636a' is the correct path to a directory containing all relevant files for a BertTokenizerFast tokenizer.
[1]    33382 segmentation fault  ./start.sh

Environment

**Open WebUI Version: current version git
**Ollama (if applicable): 0.1.44
**Operating System: Mac OS Sonoma

Reproduction Details

Confirmation:

I have read and followed all the instructions provided in the README.md.
I am on the latest version of both Open WebUI and Ollama.
I have included the browser console logs.
I have included the Docker container logs.

Logs and Screenshots

 File "/Users/wschrep/llmWork/open-webui/backend/main.py", line 43, in <module>
    from apps.rag.main import app as rag_app
  File "/Users/wschrep/llmWork/open-webui/backend/apps/rag/main.py", line 210, in <module>
    update_embedding_model(
  File "/Users/wschrep/llmWork/open-webui/backend/apps/rag/main.py", line 187, in update_embedding_model
    app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer(
  File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/sentence_transformers/SentenceTransformer.py", line 197, in __init__
    modules = self._load_sbert_model(
  File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/sentence_transformers/SentenceTransformer.py", line 1296, in _load_sbert_model
    module = Transformer(model_name_or_path, cache_dir=cache_folder, **kwargs)
  File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/sentence_transformers/models/Transformer.py", line 38, in __init__
    self.tokenizer = AutoTokenizer.from_pretrained(
  File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/transformers/models/auto/tokenization_auto.py", line 899, in from_pretrained
    return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
  File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 2094, in from_pretrained

Browser Console Logs:
[Include relevant browser console logs, if applicable]

Docker Container Logs:
[Include relevant Docker container logs, if applicable]

Screenshots (if applicable):
[Attach any relevant screenshots to help illustrate the issue]

Installation Method

[Describe the method you used to install the project, e.g., manual installation, Docker, package manager, etc.]

Additional Information

[Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.]

Note

If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!

Originally created by @w-A-L-L-e on GitHub (Jun 17, 2024). Original GitHub issue: https://github.com/open-webui/open-webui/issues/3238 # Bug Report When starting the backend with ./start.sh there seems to be a problem with the BertTokenizerFast causing a segfault: ## Description **Bug Summary:** [Provide a brief but clear summary of the bug] **Steps to Reproduce:** pip install -r requirements.txt ./start.sh **Expected Behavior:** Backend starts up and listens to a port **Actual Behavior:** Backend gives segmentation fault: ``` OSError: Can't load tokenizer for '/Users/wschrep/.cache/huggingface/hub/models--sentence-transformers--all-MiniLM-L6-v2/snapshots/8b3219a92973c328a8e22fadcfa821b5dc75636a'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure '/Users/wschrep/.cache/huggingface/hub/models--sentence-transformers--all-MiniLM-L6-v2/snapshots/8b3219a92973c328a8e22fadcfa821b5dc75636a' is the correct path to a directory containing all relevant files for a BertTokenizerFast tokenizer. [1] 33382 segmentation fault ./start.sh ``` ## Environment - **Open WebUI Version: current version git - **Ollama (if applicable): 0.1.44 - **Operating System: Mac OS Sonoma ## Reproduction Details **Confirmation:** - [ ] I have read and followed all the instructions provided in the README.md. - [ ] I am on the latest version of both Open WebUI and Ollama. - [ ] I have included the browser console logs. - [ ] I have included the Docker container logs. ## Logs and Screenshots ``` File "/Users/wschrep/llmWork/open-webui/backend/main.py", line 43, in <module> from apps.rag.main import app as rag_app File "/Users/wschrep/llmWork/open-webui/backend/apps/rag/main.py", line 210, in <module> update_embedding_model( File "/Users/wschrep/llmWork/open-webui/backend/apps/rag/main.py", line 187, in update_embedding_model app.state.sentence_transformer_ef = sentence_transformers.SentenceTransformer( File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/sentence_transformers/SentenceTransformer.py", line 197, in __init__ modules = self._load_sbert_model( File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/sentence_transformers/SentenceTransformer.py", line 1296, in _load_sbert_model module = Transformer(model_name_or_path, cache_dir=cache_folder, **kwargs) File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/sentence_transformers/models/Transformer.py", line 38, in __init__ self.tokenizer = AutoTokenizer.from_pretrained( File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/transformers/models/auto/tokenization_auto.py", line 899, in from_pretrained return tokenizer_class_fast.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs) File "/Users/wschrep/llmWork/open-webui/backend/python_env/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 2094, in from_pretrained ``` **Browser Console Logs:** [Include relevant browser console logs, if applicable] **Docker Container Logs:** [Include relevant Docker container logs, if applicable] **Screenshots (if applicable):** [Attach any relevant screenshots to help illustrate the issue] ## Installation Method [Describe the method you used to install the project, e.g., manual installation, Docker, package manager, etc.] ## Additional Information [Include any additional details that may help in understanding and reproducing the issue. This could include specific configurations, error messages, or anything else relevant to the bug.] ## Note If the bug report is incomplete or does not follow the provided instructions, it may not be addressed. Please ensure that you have followed the steps outlined in the README.md and troubleshooting.md documents, and provide all necessary information for us to reproduce and address the issue. Thank you!

GiteaMirror closed this issue

2026-04-19 19:59:02 -05:00

GiteaMirror referenced this issue

2026-04-20 04:39:02 -05:00

[PR #13185] [MERGED] fix(i18n): improve Thai translations #23127

GiteaMirror referenced this issue

2026-04-25 11:37:02 -05:00

[PR #13185] [MERGED] fix(i18n): improve Thai translations #38757

GiteaMirror referenced this issue

2026-04-29 20:52:29 -05:00

[PR #13185] [MERGED] fix(i18n): improve Thai translations #46175

GiteaMirror referenced this issue