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

chat : Granite Docling stopping (#16438)

Browse source 
* fix: Fix duplicate fake image before token on first slice

Branch: GraniteDoclingStopping

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Use double-newline before overview image

Branch: GraniteDoclingStopping

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* fix: Remove incorrect newline at the end of granite chat template gen prompt

There should not be one, even for the language models.

Branch: GraniteDoclingStopping

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

* tests: Remove bad newline from granite chat template test (legacy)

Branch: GraniteDoclingStopping

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>

---------

Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
This commit is contained in:
Gabe Goodhart 2025-10-06 10:59:40 -06:00 • committed by GitHub
parent 3a002afafa
commit c08002a198
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 3 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama-chat.cpp
View file

@ -590,7 +590,7 @@ int32_t llm_chat_apply_template(
ss << message->content << "<|end_of_text|>\n";
}
if (add_ass) {
ss << "<|start_of_role|>assistant<|end_of_role|>\n";
ss << "<|start_of_role|>assistant<|end_of_role|>";
}
} else if (tmpl == LLM_CHAT_TEMPLATE_GIGACHAT) {
// GigaChat template