Skip to content

llama-completion: respect chat_template_kwargs and reasoning_format params #25201

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
percontation wants to merge 1 commit into
base: master
Choose a base branch
from
+6 −2
Open

llama-completion: respect chat_template_kwargs and reasoning_format params #25201

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3432,7 +3432,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.default_template_kwargs[item.key()] = item.value().dump();
}
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_CHAT_TEMPLATE_KWARGS"));
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_CHAT_TEMPLATE_KWARGS"));
add_opt(common_arg(
{"-to", "--timeout"}, "N",
string_format("server read/write timeout in seconds (default: %d)", params.timeout_read),
Expand Down
6 changes: 5 additions & 1 deletion tools/completion/completion.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -156,6 +156,7 @@ int llama_completion(int argc, char ** argv) {

// note: the time for chat template initialization is not negligible:
auto chat_templates = common_chat_templates_init(model, params.chat_template);
const bool template_supports_thinking = params.use_jinja && common_chat_templates_support_enable_thinking(chat_templates.get());

@percontation percontation Jul 8, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

FWIW: this template_supports_thinking logic (plus its use below for enable_reasoning) is copied directly from server-context.cpp, for consistency with how other llama.cpp tools process these args.


// start measuring performance timings from here
llama_perf_context_reset(ctx);
Expand Down Expand Up @@ -303,9 +304,12 @@ int llama_completion(int argc, char ** argv) {

if (!params.system_prompt.empty() || !params.prompt.empty()) {
common_chat_templates_inputs inputs;
inputs.use_jinja = g_params->use_jinja;
inputs.messages = chat_msgs;
inputs.add_generation_prompt = !params.prompt.empty();
inputs.use_jinja = params.use_jinja;
inputs.reasoning_format = params.reasoning_format;
inputs.enable_thinking = params.enable_reasoning != 0 && template_supports_thinking;
inputs.chat_template_kwargs = params.default_template_kwargs;
inputs.force_pure_content = params.force_pure_content_parser;

prompt = common_chat_templates_apply(chat_templates.get(), inputs).prompt;
Expand Down