Skip to content

parallel : add option for non-shared and larger prompts #13598

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

Merged
merged 4 commits into from
May 17, 2025

Conversation

ggerganov
Copy link
Member

@ggerganov ggerganov commented May 17, 2025

  • The system prompt is now not shared by default
  • Use -pps to make the system prompt to be shared
  • Use --junk N to insert extra questions/answers in the prompt in order to simulate larger requests
  • No longer stop generation upon new-line
  • Improve the chat format
  • Update readme
# example
make -j && ./bin/llama-parallel -m ../models/gemma-3-4b/ggml-model-q8_0.gguf -np 8 -ns 128 --top-k 1 -pps --junk 10 -c 16384

@ggerganov ggerganov merged commit 518329b into master May 17, 2025
53 checks passed
@ggerganov ggerganov deleted the gg/parallel-no-shared-prompt branch May 17, 2025 09:58
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant