github ggml-org/llama.cpp b8884

3 hours ago
Details

common: Refactoring sampler parameters (#20429) (#22233)

This change refactors the reasoning_budget_message parameter from the
common params into the sampling parameters specifically. It also removes
the reasoning_budget common parameter and standardizes on the existing
reasoning_budget_tokens parameter in the sampling configuration.

Issue: #20429
Original PR: #20297

macOS/iOS:

Linux:

Android:

Windows:

openEuler:

Don't miss a new llama.cpp release

NewReleases is sending notifications on new releases.