highperfocused/ollama
1
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2025-11-11 20:47:10 +01:00
Code Issues Packages Projects Releases Wiki Activity

llm: fix seed value not being applied to requests (#4986)

Browse Source
This commit is contained in:
Jeffrey Morgan
2024-06-11 14:24:41 -07:00
committed by GitHub
parent 2ff45d571d
commit ead259d877
2 changed files with 3 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
llm/ext_server/server.cpp vendored
View File

@@ -359,7 +359,6 @@ struct llama_server_context
// slots / clients
std::vector<server_slot> slots;
json default_generation_settings_for_props;
llama_server_queue queue_tasks;
llama_server_response queue_results;
@@ -483,9 +482,6 @@ struct llama_server_context
slots.push_back(slot);
}
default_generation_settings_for_props = get_formated_generation(slots.front());
default_generation_settings_for_props["seed"] = -1;
batch = llama_batch_init(n_ctx, 0, params.n_parallel);
}
@@ -584,7 +580,7 @@ struct llama_server_context
slot->sparams.mirostat_eta = json_value(data, "mirostat_eta", default_sparams.mirostat_eta);
slot->sparams.penalize_nl = json_value(data, "penalize_nl", default_sparams.penalize_nl);
slot->params.n_keep = json_value(data, "n_keep", slot->params.n_keep);
slot->params.seed = json_value(data, "seed", default_params.seed);
slot->sparams.seed = json_value(data, "seed", default_params.seed);
slot->sparams.grammar = json_value(data, "grammar", default_sparams.grammar);
slot->sparams.n_probs = json_value(data, "n_probs", default_sparams.n_probs);
slot->sparams.min_keep = json_value(data, "min_keep", default_sparams.min_keep);
@@ -811,7 +807,6 @@ struct llama_server_context
llama_sampling_free(slot->ctx_sampling);
}
slot->ctx_sampling = llama_sampling_init(slot->sparams);
llama_set_rng_seed(ctx, slot->params.seed);
slot->command = LOAD_PROMPT;
all_slots_are_idle = false;