LLM inference in C/C++
C++ ggml
llama-batch: fix allowed decreasing pos in a seq (#25449)
Aman Gupta1ee093937fb4
diff --git a/src/llama-batch.cpp b/src/llama-batch.cppindex 5436717c42..2b98a552f4 100644--- a/src/llama-batch.cpp+++ b/src/llama-batch.cpp@@ -379,6 +379,8 @@ bool llama_batch_allocr::init(LLAMA_LOG_ERROR("%s: sequence %d positions are decreasing (not allowed)\n", __func__, seq_id);return false;}++ cur_seq_pos[seq_id] = pos;}}}