diff --git a/common/chat.cpp b/common/chat.cpp index 51053eab9..d9cdf2c03 100644 --- a/common/chat.cpp +++ b/common/chat.cpp @@ -949,6 +949,7 @@ static common_chat_msg common_chat_parse_content_only(const std::string & input) } common_chat_msg common_chat_parse(const std::string & input, common_chat_format format) { + LOG_DBG("[%s] format=%s, input:\n%s\n", __func__, common_chat_format_name(format).c_str(), input.c_str()); switch (format) { case COMMON_CHAT_FORMAT_CONTENT_ONLY: return common_chat_parse_content_only(input); diff --git a/examples/server/server.cpp b/examples/server/server.cpp index 03ed98f55..f5452b90b 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -173,6 +173,7 @@ struct slot_params { {"grammar_trigger_words", grammar_trigger_words}, {"grammar_trigger_tokens", sampling.grammar_trigger_tokens}, {"preserved_tokens", sampling.preserved_tokens}, + {"chat_format", common_chat_format_name(oaicompat_chat_format)}, {"samplers", samplers}, {"speculative.n_max", speculative.n_max}, {"speculative.n_min", speculative.n_min}, diff --git a/src/llama-grammar.cpp b/src/llama-grammar.cpp index 9b518d1ac..9c3651f3f 100644 --- a/src/llama-grammar.cpp +++ b/src/llama-grammar.cpp @@ -1186,7 +1186,7 @@ void llama_grammar_accept_impl(struct llama_grammar & grammar, llama_token token return; } } - LLAMA_LOG_DEBUG("Grammar still awaiting trigger after token %d (`%s`) (buffer: `%s`)\n", token, piece.c_str(), grammar.trigger_buffer.c_str()); + LLAMA_LOG_DEBUG("Grammar still awaiting trigger after token %d (`%s`)\n", token, piece.c_str()); // grammar.trigger_buffer.c_str() return; } }