llama : add option for greedy sampling with probs (#3813)

* llama : add option for greedy sampling with probs

* llama : add comment about llama_sample_token_greedy() missing probs

* sampling : temp == 0.0 -> no probs, temp < 0.0 -> probs

1 files changed, 1 insertions, 0 deletions

diff --git a/llama.h b/llama.h
index beac9a0c..d901dcd9 100644
--- a/llama.h
+++ b/llama.h
@@ -658,6 +658,7 @@ extern "C" {
                            float * mu);
 
     /// @details Selects the token with the highest probability.
+    ///          Does not compute the token probabilities. Use llama_sample_softmax() instead.
     LLAMA_API llama_token llama_sample_token_greedy(
             struct llama_context * ctx,
           llama_token_data_array * candidates);