From: crasm <redacted>
Date: Tue, 12 Dec 2023 09:25:57 +0000 (-0500)
Subject: llama : document logits_all deprecation (#4418)
X-Git-Tag: upstream/0.0.4488~2862
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=6391817cd19a4507c6c941a1fd08756268662b2d;p=pkg%2Fggml%2Fsources%2Fllama.cpp

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 b1f5fca6..45a65cac 100644
--- 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
     };