mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 29 Packages Projects Releases Wiki Activity

chat : add Granite 4.0 chat template with correct tool_call role mapping (#20804)

Browse Source 
* chat : add Granite 4.0 chat template with correct tool_call role mapping

Introduce `LLM_CHAT_TEMPLATE_GRANITE_4_0` alongside the existing Granite
3.x template (renamed `LLM_CHAT_TEMPLATE_GRANITE_3_X`).

The Granite 4.0 Jinja template uses `<tool_call>` XML tags and maps the
`assistant_tool_call` role to `<|start_of_role|>assistant<|end_of_role|><|tool_call|>`.
Without a matching C++ handler, the fallback path emits the literal role
`assistant_tool_call` which the model does not recognize, breaking tool
calling when `--jinja` is not used.

Changes:
- Rename `LLM_CHAT_TEMPLATE_GRANITE` to `LLM_CHAT_TEMPLATE_GRANITE_3_X`
  (preserves existing 3.x behavior unchanged)
- Add `LLM_CHAT_TEMPLATE_GRANITE_4_0` enum, map entry, and handler
- Detection: `<|start_of_role|>` + (`<tool_call>` or `<tools>`) → 4.0,
  otherwise → 3.x
- Add production Granite 4.0 Jinja template
- Add tests for both 3.x and 4.0 template paths (C++ and Jinja)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* Code review: follow standard format and use common logic in test-chat-template.cpp

* Rename custom_conversation variable for extra_conversation to give it a more meaningful name

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Jesus Talavera
2026-04-02 11:28:56 +02:00
committed by GitHub
parent 17193cce34
commit 6137c325a1
5 changed files with 189 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/test-chat-template.cpp
+31 -4
View File
@@ -354,6 +354,7 @@ int main_automated_tests(void) {
std::string bos_token = "";
std::string eos_token = "";
bool supported_with_jinja = true;
std::vector<llama_chat_message> extra_conversation = {};
};
std::vector<TestCase> test_cases {
{
@@ -604,6 +605,26 @@ int main_automated_tests(void) {
/* .expected_output_jinja= */ "<seed:bos>system\nYou are a helpful assistant<seed:eos><seed:bos>user\nHello<seed:eos><seed:bos>assistant\nHi there<seed:eos><seed:bos>user\nWho are you<seed:eos><seed:bos>assistant\nI am an assistant<seed:eos><seed:bos>user\nAnother question<seed:eos><seed:bos>assistant\n",
/* .bos_token= */ "<seed:bos>",
/* .eos_token= */ "<seed:eos>",
},
{
/* .name= */ "ibm-granite/granite-3.x (tool call)",
/* .template_str= */ "{%- for message in messages %}\n {%- if message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- else %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n {%- endif %}\n{%- endfor %}",
/* .expected_output= */ "<|start_of_role|>system<|end_of_role|>You are a helpful assistant<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Hello<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>Hi there<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Who are you<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|> I am an assistant <|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Another question<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>What is the weather?<|end_of_text|>\n<|start_of_role|>assistant_tool_call<|end_of_role|><|tool_call|>[{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}]<|end_of_text|>\n<|start_of_role|>tool_response<|end_of_role|>{\"temperature\": 72}<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>",
/* .expected_output_jinja= */ "<|start_of_role|>system<|end_of_role|>You are a helpful assistant<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Hello<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>Hi there<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Who are you<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|> I am an assistant <|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Another question<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>What is the weather?<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|><|tool_call|>[{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}]<|end_of_text|>\n<|start_of_role|>tool_response<|end_of_role|>{\"temperature\": 72}<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>",
/* .bos_token= */ "",
/* .eos_token= */ "",
/* .supported_with_jinja= */ true,
/* .extra_conversation= */ {{"user", "What is the weather?"}, {"assistant_tool_call", "[{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}]"}, {"tool_response", "{\"temperature\": 72}"}},
},
{
/* .name= */ "ibm-granite/granite-4.0 (tool call)",
/* .template_str= */ "{%- for message in messages %}\n {%- if message['role'] == 'assistant_tool_call' %}\n {{- '<|start_of_role|>assistant<|end_of_role|><|tool_call|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- else %}\n {{- '<|start_of_role|>' + message['role'] + '<|end_of_role|>' + message['content'] + '<|end_of_text|>\\n' }}\n {%- endif %}\n {%- if loop.last and add_generation_prompt %}\n {{- '<|start_of_role|>assistant<|end_of_role|>' }}\n {%- endif %}\n{%- endfor %}\n{# <tool_call> <tools> #}",
/* .expected_output= */ "<|start_of_role|>system<|end_of_role|>You are a helpful assistant<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Hello<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>Hi there<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Who are you<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|> I am an assistant <|end_of_text|>\n<|start_of_role|>user<|end_of_role|>Another question<|end_of_text|>\n<|start_of_role|>user<|end_of_role|>What is the weather?<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|><|tool_call|><tool_call>\n{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}\n</tool_call><|end_of_text|>\n<|start_of_role|>tool_response<|end_of_role|>{\"temperature\": 72}<|end_of_text|>\n<|start_of_role|>assistant<|end_of_role|>",
/* .expected_output_jinja= */ "",
/* .bos_token= */ "",
/* .eos_token= */ "",
/* .supported_with_jinja= */ true,
/* .extra_conversation= */ {{"user", "What is the weather?"}, {"assistant_tool_call", "<tool_call>\n{\"name\": \"get_weather\", \"arguments\": {\"location\": \"NYC\"}}\n</tool_call>"}, {"tool_response", "{\"temperature\": 72}"}},
}
};
std::vector<char> formatted_chat(1024);
@@ -627,11 +648,13 @@ int main_automated_tests(void) {
for (const auto & test_case : test_cases) {
std::cout << "\n\n=== " << test_case.name << " ===\n\n";
formatted_chat.resize(1024);
auto conv = conversation;
conv.insert(conv.end(), test_case.extra_conversation.begin(), test_case.extra_conversation.end());
formatted_chat.resize(2048);
res = llama_chat_apply_template(
test_case.template_str.c_str(),
conversation.data(),
conversation.size(),
conv.data(),
conv.size(),
add_generation_prompt,
formatted_chat.data(),
formatted_chat.size()
@@ -658,11 +681,15 @@ int main_automated_tests(void) {
}
std::cout << "\n\n=== " << test_case.name << " (jinja) ===\n\n";
try {
auto msgs = messages;
for (const auto & msg : test_case.extra_conversation) {
msgs.push_back(simple_msg(msg.role, msg.content));
}
auto output = format_using_common(
test_case.template_str,
test_case.bos_token,
test_case.eos_token,
messages);
msgs);
auto expected_output = normalize_newlines(test_case.expected_output_jinja.empty() ? test_case.expected_output : test_case.expected_output_jinja);
if (output != expected_output) {
std::cout << "Template:```\n" << test_case.template_str << "\n```";