sampling: fix top_k <= 0 (#5388)

* sampling: fix top_k <= 0 * Update llama.cpp Co-authored-by: Georgi Gerganov <[email protected]> --------- Co-authored-by: Georgi Gerganov <[email protected]>
2024-02-08 09:46:30 +01:00
parent 8504d2d0da
commit 26d4efd11e
3 changed files with 7 additions and 1 deletions
@@ -8585,6 +8585,10 @@ void llama_sample_top_k(struct llama_context * ctx, llama_token_data_array * can
    // }

    const int64_t t_start_sample_us = ggml_time_us();
+    
+    if (k <= 0) {
+        k = candidates->size;
+    }

    k = std::max(k, (int) min_keep);
    k = std::min(k, (int) candidates->size);