mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-11-09 05:14:35 +01:00
cli : fix reasoning responses in CLI (#18961)
* cli : fix reasoning responses in CLI * fix build * fix build (2)
This commit is contained in:
@@ -274,6 +274,7 @@ std::vector<server_tokens> tokenize_input_prompts(
|
||||
// OAI utils
|
||||
//
|
||||
|
||||
// global server parameters for chat formatting / parsing
|
||||
struct server_chat_params {
|
||||
bool use_jinja;
|
||||
bool prefill_assistant;
|
||||
|
||||
Reference in New Issue
Block a user