happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

add missing parameters in `server-task.cpp`

This commit is contained in:
ddh0 2025-12-12 22:39:51 -06:00
parent 5c78b7927f
commit 53380c183f
1 changed files with 27 additions and 25 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
tools/server/server-task.cpp
View File

@ -182,31 +182,33 @@ task_params server_task::params_from_json_cmpl(
params.t_max_predict_ms = json_value(data, "t_max_predict_ms", defaults.t_max_predict_ms); params.t_max_predict_ms = json_value(data, "t_max_predict_ms", defaults.t_max_predict_ms);
params.response_fields = json_value(data, "response_fields", std::vector<std::string>()); params.response_fields = json_value(data, "response_fields", std::vector<std::string>());
params.sampling.top_k = json_value(data, "top_k", defaults.sampling.top_k); params.sampling.top_k = json_value(data, "top_k", defaults.sampling.top_k);
params.sampling.top_p = json_value(data, "top_p", defaults.sampling.top_p); params.sampling.top_p = json_value(data, "top_p", defaults.sampling.top_p);
params.sampling.min_p = json_value(data, "min_p", defaults.sampling.min_p); params.sampling.min_p = json_value(data, "min_p", defaults.sampling.min_p);
params.sampling.top_n_sigma = json_value(data, "top_n_sigma", defaults.sampling.top_n_sigma); params.sampling.top_n_sigma = json_value(data, "top_n_sigma", defaults.sampling.top_n_sigma);
params.sampling.xtc_probability = json_value(data, "xtc_probability", defaults.sampling.xtc_probability); params.sampling.xtc_probability = json_value(data, "xtc_probability", defaults.sampling.xtc_probability);
params.sampling.xtc_threshold = json_value(data, "xtc_threshold", defaults.sampling.xtc_threshold); params.sampling.xtc_threshold = json_value(data, "xtc_threshold", defaults.sampling.xtc_threshold);
params.sampling.typ_p = json_value(data, "typical_p", defaults.sampling.typ_p); params.sampling.typ_p = json_value(data, "typical_p", defaults.sampling.typ_p);
params.sampling.temp = json_value(data, "temperature", defaults.sampling.temp); params.sampling.temp = json_value(data, "temperature", defaults.sampling.temp);
params.sampling.dynatemp_range = json_value(data, "dynatemp_range", defaults.sampling.dynatemp_range); params.sampling.dynatemp_range = json_value(data, "dynatemp_range", defaults.sampling.dynatemp_range);
params.sampling.dynatemp_exponent = json_value(data, "dynatemp_exponent", defaults.sampling.dynatemp_exponent); params.sampling.dynatemp_exponent = json_value(data, "dynatemp_exponent", defaults.sampling.dynatemp_exponent);
params.sampling.penalty_last_n = json_value(data, "repeat_last_n", defaults.sampling.penalty_last_n); params.sampling.penalty_last_n = json_value(data, "repeat_last_n", defaults.sampling.penalty_last_n);
params.sampling.penalty_repeat = json_value(data, "repeat_penalty", defaults.sampling.penalty_repeat); params.sampling.penalty_repeat = json_value(data, "repeat_penalty", defaults.sampling.penalty_repeat);
params.sampling.penalty_freq = json_value(data, "frequency_penalty", defaults.sampling.penalty_freq); params.sampling.penalty_freq = json_value(data, "frequency_penalty", defaults.sampling.penalty_freq);
params.sampling.penalty_present = json_value(data, "presence_penalty", defaults.sampling.penalty_present); params.sampling.penalty_present = json_value(data, "presence_penalty", defaults.sampling.penalty_present);
params.sampling.dry_multiplier = json_value(data, "dry_multiplier", defaults.sampling.dry_multiplier); params.sampling.dry_multiplier = json_value(data, "dry_multiplier", defaults.sampling.dry_multiplier);
params.sampling.dry_base = json_value(data, "dry_base", defaults.sampling.dry_base); params.sampling.dry_base = json_value(data, "dry_base", defaults.sampling.dry_base);
params.sampling.dry_allowed_length = json_value(data, "dry_allowed_length", defaults.sampling.dry_allowed_length); params.sampling.dry_allowed_length = json_value(data, "dry_allowed_length", defaults.sampling.dry_allowed_length);
params.sampling.dry_penalty_last_n = json_value(data, "dry_penalty_last_n", defaults.sampling.dry_penalty_last_n); params.sampling.dry_penalty_last_n = json_value(data, "dry_penalty_last_n", defaults.sampling.dry_penalty_last_n);
params.sampling.mirostat = json_value(data, "mirostat", defaults.sampling.mirostat); params.sampling.mirostat = json_value(data, "mirostat", defaults.sampling.mirostat);
params.sampling.mirostat_tau = json_value(data, "mirostat_tau", defaults.sampling.mirostat_tau); params.sampling.mirostat_tau = json_value(data, "mirostat_tau", defaults.sampling.mirostat_tau);
params.sampling.mirostat_eta = json_value(data, "mirostat_eta", defaults.sampling.mirostat_eta); params.sampling.mirostat_eta = json_value(data, "mirostat_eta", defaults.sampling.mirostat_eta);
params.sampling.seed = json_value(data, "seed", defaults.sampling.seed); params.sampling.power_law_target = json_value(data, "power_law_target", defaults.sampling.power_law_target);
params.sampling.n_probs = json_value(data, "n_probs", defaults.sampling.n_probs); params.sampling.power_law_window_size = json_value(data, "power_law_window_size", defaults.sampling.power_law_window_size);
params.sampling.min_keep = json_value(data, "min_keep", defaults.sampling.min_keep); params.sampling.seed = json_value(data, "seed", defaults.sampling.seed);
params.post_sampling_probs = json_value(data, "post_sampling_probs", defaults.post_sampling_probs); params.sampling.n_probs = json_value(data, "n_probs", defaults.sampling.n_probs);
params.sampling.min_keep = json_value(data, "min_keep", defaults.sampling.min_keep);
params.post_sampling_probs = json_value(data, "post_sampling_probs", defaults.post_sampling_probs);
params.speculative.n_min = json_value(data, "speculative.n_min", defaults.speculative.n_min); params.speculative.n_min = json_value(data, "speculative.n_min", defaults.speculative.n_min);
params.speculative.n_max = json_value(data, "speculative.n_max", defaults.speculative.n_max); params.speculative.n_max = json_value(data, "speculative.n_max", defaults.speculative.n_max);