From af0a5b616359809ce886ea433acedebb39b12969 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Johannes=20G=C3=A4=C3=9Fler?= <johannesg@5d6.de>
Date: Tue, 7 May 2024 23:07:58 +0200
Subject: server: fix incorrectly reported token probabilities (#7125)

* server: normalize token probabilities

* fix temperature == 0.0f
---
 common/sampling.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'common/sampling.h')

diff --git a/common/sampling.h b/common/sampling.h
index cf7081e3..5b73ecdc 100644
--- a/common/sampling.h
+++ b/common/sampling.h
@@ -81,6 +81,7 @@ struct llama_sampling_context {
     // TODO: replace with ring-buffer
     std::vector<llama_token>      prev;
     std::vector<llama_token_data> cur;
+    size_t n_considered;
 
     std::mt19937 rng;
 };
-- 
cgit v1.2.3