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

chat : nemotron thinking & toolcalling support (#15676)

Browse source 
* feat: nemotron thinking & toolcalling support

* Trailing whitespaces

* Corrected template for Nemotron

* Template and parser fixes

* Final template and grammar changes

* Whitespace

* Always do lazy grammar processing since </think> tag will always be there.

* Allow extra content after toolcall

* Whitespace

* New tests: thinking + tools, tools + content, thinking + tools + content (new!)

* Whitespace

* Remove cURL test script
This commit is contained in:
Piotr Wilkin (ilintar) 2025-09-05 01:22:22 +02:00 • committed by GitHub
parent 9e2b1e83c6
commit b2426e469e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 333 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
common/chat.h
View file

@ -112,6 +112,7 @@ enum common_chat_format {
COMMON_CHAT_FORMAT_GRANITE,
COMMON_CHAT_FORMAT_GPT_OSS,
COMMON_CHAT_FORMAT_SEED_OSS,
COMMON_CHAT_FORMAT_NEMOTRON_V2,
COMMON_CHAT_FORMAT_COUNT, // Not a format, just the # formats
};