thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

Autoparser - complete refactoring of parser architecture (#18675)

Browse source 
* Autoparser - full single commit squish

* Final pre-merge changes: minor fixes, Kimi 2.5 model parser
This commit is contained in:
Piotr Wilkin (ilintar) 2026-03-06 21:01:00 +01:00 • committed by GitHub
parent 34df42f7be
commit 566059a26b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
63 changed files with 12967 additions and 10071 deletions
Download patch file Download diff file Expand all files Collapse all files

4
tools/cli/cli.cpp
View file

@ -1,3 +1,4 @@
#include "chat.h"
#include "common.h"
#include "arg.h"
#include "console.h"
@ -191,7 +192,8 @@ struct cli_context {
inputs.use_jinja = chat_params.use_jinja;
inputs.parallel_tool_calls = false;
inputs.add_generation_prompt = true;
inputs.enable_thinking = chat_params.enable_thinking;
inputs.reasoning_format = COMMON_REASONING_FORMAT_DEEPSEEK;
inputs.enable_thinking = common_chat_templates_support_enable_thinking(chat_params.tmpls.get());
// Apply chat template to the list of messages
return common_chat_templates_apply(chat_params.tmpls.get(), inputs);