kv-cells : fix tracking of seq_pos (#14339)

* kv-cells : fix tracking of seq_pos during cache reuse ggml-ci * cont : improve error message ggml-ci * cont : add more comments
2025-06-23 12:27:35 +03:00 · 2025-06-23 12:27:35 +03:00 · 7b50d589a8
commit 7b50d589a8
parent 3a9457df96
5 changed files with 56 additions and 17 deletions
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@ -1018,7 +1018,6 @@ int llama_context::decode(const llama_batch & batch_inp) {
                pos_min[s] = std::numeric_limits<llama_pos>::max();
            }

-            // TODO: fix sequence indexing
            for (uint32_t i = 0; i < ubatch.n_tokens; ++i) {
                const auto & seq_id = ubatch.seq_id[i][0];