-
Notifications
You must be signed in to change notification settings - Fork 32
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
Solved incident "llm_lazy" - "llm_summary" running against coolstore and llama3 is seeing multiple issues #382
Comments
Below is an example from above run that completed. It's been ~75 minutes since I kicked off run_demo.py. $ gist ShoppingCart.java.prompts.md $ gist ShoppingCart.java.llm_result.md $ gist ShoppingCart.java.llm_response_metadata.json |
Example of what I'm seeing with run_demo.py
|
run_demo.py
against coolstore with llama3 served from IBM BAM.I am running with an alternate configuration where I explicitly enabled the solution_producers "llm_lazy".
As I did this I have not seen a single fix come back to the run_demo.py client, it's been close to 60 minutes now since I first kicked this off.
I am seeing multiple problems:
Processing run_demo.py ran for 6 hours: 9:30am - 3:30pm and then stopped. Many timeouts and errors
~10 minutes of no activity in server logs, and then I saw:
pom.xml
waited an additional ~40 minutes past the prior error and have not see any other activity from other files in the server console
kai.models.file_solution - [ file_solution.py:23 - guess_language()]
After ~75 minutes, most of the requests from the client
run_demo.py
have timed out, I have seen 1 file succeed, rest timeouts (10 minute timeout)ERROR - 2024-09-21 10:35:09,636 - __main__ - [ run_demo.py:61 - generate_fix()] - [src/main/java/com/redhat/coolstore/model/ShoppingCart.java] Received exception: HTTPConnectionPool(host='0.0.0.0', port=8080): Read timed out. (read timeout=3600)
Seeing
[CRITICAL] WORKER TIMEOUT (pid:18881)
server sideServer console output: https://gist.github.com/jwmatthews/a60f2a36b5691b466d9964386c61d04b
Full kai_server log: https://gist.githubusercontent.com/jwmatthews/c93bbd785643422f07d122f10635471a/raw/9423743b874ae61c95dfd2967f69f78e8c7fb190/kai_server.log
Full run_demo.py console output:
https://gist.github.com/jwmatthews/5af0c32bc7951fffbf4be6c302a5e7d0
Looking at one example of
pom.xml
traceback: https://gist.github.com/jwmatthews/7c5a6e4d24bf445c35d972013cad4729Sample error from pom.xml:
The config I am running with
The text was updated successfully, but these errors were encountered: