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

deps: update llama.cpp #99

Merged
merged 1 commit into from
Sep 10, 2024
Merged

deps: update llama.cpp #99

merged 1 commit into from
Sep 10, 2024

Conversation

quitrk
Copy link
Collaborator

@quitrk quitrk commented Sep 10, 2024

  • this fixes timeouts when running llama 3.1
  • bypass storing failed jobs in redis if they were ran with external processor

- this fixes timeouts when running llama 3.1
- bypass storing failed jobs in redis if they were ran with external processor
@quitrk quitrk requested a review from saghul September 10, 2024 08:23
@saghul
Copy link
Member

saghul commented Sep 10, 2024

Out of curiosity what commit in llama.cpp fixed it?

@quitrk
Copy link
Collaborator Author

quitrk commented Sep 10, 2024

Out of curiosity what commit in llama.cpp fixed it?

I traced the fix back to two commits.

ggerganov/llama.cpp@4b9afbb
ggerganov/llama.cpp@06658ad

Now, the second one seems mac related, so I'll have to test some more on the A10 after I deploy in stage

@quitrk quitrk merged commit 6ccb949 into master Sep 10, 2024
@quitrk quitrk deleted the tavram/timeouts branch September 10, 2024 08:55
@saghul
Copy link
Member

saghul commented Sep 10, 2024

🙌🙌

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

Successfully merging this pull request may close these issues.

2 participants