In a multi-round conversation, what does the trace of the n-th round represent？
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 682
- Forks
- 128
- Avg merge
- 9h 44m
- Merged PRs (30d)
- 1
Description
Does the num_prefill_tokens for round n correspond solely to the prompt of that round, or does it include all prompts from rounds 1 to n and the outputs from rounds 1 to n–1? If it includes the full prompt and output history, could it easily exceed the request length threshold?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No file, test, or entry point is named. Start by locating the trace generation and the calculation of num_prefill_tokens, then follow how multi-round prompts and outputs are represented. Done means documenting whether the value is per-round or cumulative and how request-length thresholds apply.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Documentation
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100