Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ipex-llm][cpp][ollama]nonsense output when running infer simultaneously (OLLAMA_NUM_PARALLEL!=1) #12835

Open
jianjungu opened this issue Feb 17, 2025 · 0 comments
Assignees

Comments

@jianjungu
Copy link

jianjungu commented Feb 17, 2025

If set the ollama environment para OLLAMA_NUM_PARALLEL=2 or other values not equal to 1, the output is broken. This issue can be reproduced on my laptops LNL 258V and ARL-H 255H.

the reproduce python code is attached
issue_multi_request.zip

The ollama version is 20250122
I start ollama service with default value (OLLAMA_NUM_PARALLEL:0 or set OLLAMA_NUM_PARALLEL=2)
Image

  • If open one python window and run the reproduce code

python issue_multi_request.py

the output is OK

Image
  • if open two python window and run the code in each window simultaneously,

the output is wrong

Image
  • if the infer is running on CPU , the output is ok

  • if set OLLAMA_NUM_PARALLEL=1, the output is OK

Image Image
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

3 participants