llama : document logits_all deprecation (#4418)

llama_context_params.logits_all is a parameter for controlling
llama_eval. This documents that logits_all should not be used with
llama_decode and llama_batch.

diff --git a/llama.h b/llama.h
index b1f5fca624d69def6989d0f0c1af7538448563ed..45a65cacb7bb8e76f038d5fc3f6929fdf8be3232 100644 (file)
--- a/llama.h
+++ b/llama.h
@@ -216,7 +216,7 @@ extern "C" {
 
         // Keep the booleans together to avoid misalignment during copy-by-value.
         bool mul_mat_q;   // if true, use experimental mul_mat_q kernels (DEPRECATED - always true)
-        bool logits_all;  // the llama_eval() call computes all logits, not just the last one
+        bool logits_all;  // the llama_eval() call computes all logits, not just the last one (DEPRECATED - set llama_batch.logits instead)
         bool embedding;   // embedding mode only
         bool offload_kqv; // whether to offload the KQV ops (including the KV cache) to GPU
     };