mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-19 17:24:57 +02:00
Enable backend sampling with token speculation
This commit is contained in:
@@ -216,6 +216,7 @@ static struct llama_sampler_i common_reasoning_budget_i = {
|
||||
/* .backend_init = */ nullptr,
|
||||
/* .backend_accept = */ nullptr,
|
||||
/* .backend_apply = */ nullptr,
|
||||
/* .backend_reset = */ nullptr,
|
||||
/* .backend_set_input = */ nullptr,
|
||||
};
|
||||
|
||||
|
||||
Reference in New Issue
Block a user