]>
git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
speculative : fix n_outputs_max and remove draft-simple auto-enable (#23988)
* speculative : add common_speculative_n_max helper function
Extract the speculative max-draft-size logic from server_n_outputs_max
into a reusable common_speculative_n_max() function in common/speculative.
Assisted-by: llama.cpp:local pi
* cont : draft context always has n_parallel outputs
* llama : log n_outputs_max
* speculative : remove draft-simple auto-enable
* ci : enable server tests on PRs
overview / pkg / ggml / sources / llama.cpp / commit