Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

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

Jeffrey Morganead259d877fc
diff --git a/docs/api.md b/docs/api.md
index f761f68c9..35f1def33 100644
--- a/docs/api.md
+++ b/docs/api.md
@@ -250,7 +250,7 @@ curl http://localhost:11434/api/generate -d '{
#### Request (Reproducible outputs)
-For reproducible outputs, set `temperature` to 0 and `seed` to a number:
+For reproducible outputs, set `seed` to a number:
##### Request
@@ -259,8 +259,7 @@ curl http://localhost:11434/api/generate -d '{
"model": "mistral",
"prompt": "Why is the sky blue?",
"options": {
- "seed": 123,
- "temperature": 0
+ "seed": 123
}
}'
```
diff --git a/llm/ext_server/server.cpp b/llm/ext_server/server.cpp
index 7d14e48ed..93e715627 100644
--- a/llm/ext_server/server.cpp
+++ b/llm/ext_server/server.cpp
@@ -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;