From cf0e1475c59e3e609e6cce89deb626a20f2682bf Mon Sep 17 00:00:00 2001 From: Daniel Bevenius Date: Mon, 1 Dec 2025 09:13:47 +0100 Subject: [PATCH] sampling : lower log level for output buffer reallocations [no ci] This commit changes the logging level for output buffer reallocations in the llama_context::output_reserve function from INFO to DEBUG. The motivation for this is that it currently logs to info and when enabling verbose logging for llama-cli this will get mixed with the output, for example: ```console What is the capital of Sweden?output_reserve: reallocating output buffer from size 0.58 MiB to 1.74 MiB 1. Stockholm 2\. Helsinki Based are the options 1. Stockholm Explanation: Stockholm is the capital of ... ``` --- src/llama-context.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama-context.cpp b/src/llama-context.cpp index 7f7b838e14..78f12011c4 100644 --- a/src/llama-context.cpp +++ b/src/llama-context.cpp @@ -1718,7 +1718,7 @@ uint32_t llama_context::output_reserve(int32_t n_outputs, const llama_batch & ba if (buf_output) { #ifndef NDEBUG // This doesn't happen often, but may be annoying in some cases (like the HellaSwag benchmark) - LLAMA_LOG_INFO("%s: reallocating output buffer from size %.02f MiB to %.02f MiB\n", __func__, prev_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0); + LLAMA_LOG_DEBUG("%s: reallocating output buffer from size %.02f MiB to %.02f MiB\n", __func__, prev_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0); #endif buf_output = nullptr; logits = nullptr;