mlcommons / mlcommons/inference
Llama3.1-405B non-zero temperature
Open
Nobody has claimed this yet.
inference v5.0
- Dominant language
- Python
- Stars
- 1.6k
- Forks
- 650
- Avg merge
- 1d 22h
- Merged PRs (30d)
- 6
Description
In the reference implementation of Llama3.1-405B, temperature is set to 1. Is this intentional?
Normally, temperature should be set to zero for outputs for be more deterministic. Can an optimized implementation use a different temperature?
Contributor guide
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
Start with the temperature assignment at language/llama3.1-405b/SUT_vLLM.py line 71 and inspect how the reference implementation uses it. Compare the intended determinism of temperature zero with the question of whether optimized implementations may use another value; done means the project’s expected behavior is established and consistently documented or tested.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100