Skip to content

fix(llama-cpp): Pass parameters when using embedded template #8590

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

Merged
mudler merged 1 commit into from
Feb 17, 2026
Merged

fix(llama-cpp): Pass parameters when using embedded template #8590

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
72 changes: 72 additions & 0 deletions backend/cpp/llama-cpp/grpc-server.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1261,6 +1261,42 @@ class BackendServiceImpl final : public backend::Backend::Service {
body_json["add_generation_prompt"] = data["add_generation_prompt"];
}

// Pass sampling parameters to body_json so oaicompat_chat_params_parse respects them
// and doesn't overwrite them with defaults in the returned parsed_data
if (data.contains("n_predict")) {
body_json["max_tokens"] = data["n_predict"];
}
if (data.contains("ignore_eos")) {
body_json["ignore_eos"] = data["ignore_eos"];
}
if (data.contains("stop")) {
body_json["stop"] = data["stop"];
}
if (data.contains("temperature")) {
body_json["temperature"] = data["temperature"];
}
if (data.contains("top_p")) {
body_json["top_p"] = data["top_p"];
}
if (data.contains("frequency_penalty")) {
body_json["frequency_penalty"] = data["frequency_penalty"];
}
if (data.contains("presence_penalty")) {
body_json["presence_penalty"] = data["presence_penalty"];
}
if (data.contains("seed")) {
body_json["seed"] = data["seed"];
}
if (data.contains("logit_bias")) {
body_json["logit_bias"] = data["logit_bias"];
}
if (data.contains("top_k")) {
body_json["top_k"] = data["top_k"];
}
if (data.contains("min_p")) {
body_json["min_p"] = data["min_p"];
}

// Debug: Print full body_json before template processing (includes messages, tools, tool_choice, etc.)
SRV_DBG("[CONVERSATION DEBUG] PredictStream: Full body_json before oaicompat_chat_params_parse:\n%s\n", body_json.dump(2).c_str());

Expand Down Expand Up @@ -1992,6 +2028,42 @@ class BackendServiceImpl final : public backend::Backend::Service {
body_json["add_generation_prompt"] = data["add_generation_prompt"];
}

// Pass sampling parameters to body_json so oaicompat_chat_params_parse respects them
// and doesn't overwrite them with defaults in the returned parsed_data
if (data.contains("n_predict")) {
body_json["max_tokens"] = data["n_predict"];
}
if (data.contains("ignore_eos")) {
body_json["ignore_eos"] = data["ignore_eos"];
}
if (data.contains("stop")) {
body_json["stop"] = data["stop"];
}
if (data.contains("temperature")) {
body_json["temperature"] = data["temperature"];
}
if (data.contains("top_p")) {
body_json["top_p"] = data["top_p"];
}
if (data.contains("frequency_penalty")) {
body_json["frequency_penalty"] = data["frequency_penalty"];
}
if (data.contains("presence_penalty")) {
body_json["presence_penalty"] = data["presence_penalty"];
}
if (data.contains("seed")) {
body_json["seed"] = data["seed"];
}
if (data.contains("logit_bias")) {
body_json["logit_bias"] = data["logit_bias"];
}
if (data.contains("top_k")) {
body_json["top_k"] = data["top_k"];
}
if (data.contains("min_p")) {
body_json["min_p"] = data["min_p"];
}

// Debug: Print full body_json before template processing (includes messages, tools, tool_choice, etc.)
SRV_DBG("[CONVERSATION DEBUG] Predict: Full body_json before oaicompat_chat_params_parse:\n%s\n", body_json.dump(2).c_str());

Expand Down
Loading