Skip to content

Conversation

@ggerganov
Copy link
Member

Better defaults for speculative decoding.

@ggerganov ggerganov merged commit abd4d0b into master Feb 19, 2025
46 checks passed
orca-zhang pushed a commit to orca-zhang/llama.cpp that referenced this pull request Feb 26, 2025
* speculative : update default params

* speculative : do not discard the last drafted token
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Feb 26, 2025
* speculative : update default params

* speculative : do not discard the last drafted token
mglambda pushed a commit to mglambda/llama.cpp that referenced this pull request Mar 8, 2025
* speculative : update default params

* speculative : do not discard the last drafted token
mostlyuseful pushed a commit to mostlyuseful/llama.cpp that referenced this pull request May 12, 2025
* speculative : update default params

* speculative : do not discard the last drafted token
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants