mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-10-27 08:21:30 +00:00
server : only attempt to enable thinking if using jinja (#15967)
This commit is contained in:
@@ -2313,7 +2313,7 @@ struct server_context {
|
|||||||
// thinking is enabled if:
|
// thinking is enabled if:
|
||||||
// 1. It's not explicitly disabled (reasoning_budget == 0)
|
// 1. It's not explicitly disabled (reasoning_budget == 0)
|
||||||
// 2. The chat template supports it
|
// 2. The chat template supports it
|
||||||
const bool enable_thinking = params_base.reasoning_budget != 0 && common_chat_templates_support_enable_thinking(chat_templates.get());
|
const bool enable_thinking = params_base.use_jinja && params_base.reasoning_budget != 0 && common_chat_templates_support_enable_thinking(chat_templates.get());
|
||||||
SRV_INF("Enable thinking? %d\n", enable_thinking);
|
SRV_INF("Enable thinking? %d\n", enable_thinking);
|
||||||
|
|
||||||
oai_parser_opt = {
|
oai_parser_opt = {
|
||||||
|
|||||||
Reference in New Issue
Block a user