From: matiaslin <redacted>
Date: Sun, 29 Sep 2024 12:25:00 +0000 (-0700)
Subject: common : ensure llama_batch size does not exceed max size (#9668)
X-Git-Tag: upstream/0.0.4488~646
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=faac0bae265449fd988c57bf894018edc36fbe1e;p=pkg%2Fggml%2Fsources%2Fllama.cpp

common : ensure llama_batch size does not exceed max size (#9668)

A crash was observed when the number of tokens added to a batch exceeds
llama_batch size. An assertion in llama_batch_add was added to protect
against llama_batch size overflow.
---

diff --git a/common/common.cpp b/common/common.cpp
index e2b8574b..a0611f3d 100644
--- a/common/common.cpp
+++ b/common/common.cpp
@@ -1437,6 +1437,8 @@ void llama_batch_add(
                           llama_pos   pos,
     const std::vector<llama_seq_id> & seq_ids,
                                bool   logits) {
+    GGML_ASSERT(batch.seq_id[batch.n_tokens] && "llama_batch size exceeded");
+
     batch.token   [batch.n_tokens] = id;
     batch.pos     [batch.n_tokens] = pos;
     batch.n_seq_id[batch.n_tokens] = seq_ids.size();